© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 4973
    Prev
    Next
    INDEX
    Explanations

    Chemical receptors/compounds

    np_max-act · gemini-2.0-flash

    specialized scientific/technical jargon and research-style formatting (e.g., dense terminology, acronyms, nomenclature, assays, and citation markup) in academic texts.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    联手
    -0.08
     zrobić
    -0.08
     ihr
    -0.07
    ıyorum
    -0.07
    心动
    -0.07
    ворот
    -0.07
     그렇게
    -0.07
    贴心
    -0.07
     отлично
    -0.07
    mort
    -0.07
    POSITIVE LOGITS
    1
    0.25
     of
    0.19
    ↵↵
    0.18
    的
    0.17
    .↵↵
    0.16
    .↵
    0.16
    ↵
    0.15
    2
    0.14
     (
    0.14
    ↵
    0.14
    Activations Density 14.083%

    No Known Activations