Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 71552
    Prev
    Next
    INDEX
    Explanations

    restoring previous version

    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
     người
    -0.07
     Georgian
    -0.07
     norske
    -0.07
    독
    -0.06
     Người
    -0.06
    reland
    -0.06
    ADOR
    -0.06
    upgrade
    -0.06
    _physical
    -0.06
     ki
    -0.06
    POSITIVE LOGITS
     necessities
    0.07
    隋
    0.07
     incompatible
    0.06
    .z
    0.06
    PAR
    0.06
     далеко
    0.06
     no
    0.06
    ANDARD
    0.06
    '.↵↵
    0.06
    .previous
    0.06
    Activations Density 0.029%

    No Known Activations