© 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. 19-RESID-POST-AA
    11. 70600
    Prev
    Next
    INDEX
    Explanations

    adget

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lemen
    -0.07
     dần
    -0.07
    胧
    -0.07
     simplified
    -0.07
    红星
    -0.06
    辈
    -0.06
     pour
    -0.06
    ('(
    -0.06
    🤗
    -0.06
    역
    -0.06
    POSITIVE LOGITS
     venues
    0.08
    뛰
    0.07
    훼
    0.07
    浃
    0.07
     palace
    0.07
    IA
    0.07
    vinfos
    0.07
     wiped
    0.07
     ba
    0.07
     licensee
    0.07
    Activations Density 0.009%

    No Known Activations