© 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. 61124
    Prev
    Next
    INDEX
    Explanations

    technical, code-like, and formally structured text such as APIs, logs, specs, and scientific/procedural writing.

    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
    1
    -0.24
    ↵↵
    -0.17
    .↵
    -0.17
     of
    -0.17
    .↵↵
    -0.17
    的
    -0.16
    ↵
    -0.15
     (
    -0.14
    ↵
    -0.14
    2
    -0.14
    POSITIVE LOGITS
    联手
    0.08
    .teacher
    0.08
    ворот
    0.07
    .frequency
    0.07
    mort
    0.07
     그렇게
    0.07
     zrobić
    0.07
    心动
    0.07
     youre
    0.06
    _AD
    0.06
    Activations Density 10.184%

    No Known Activations