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. 129447
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     AlertDialog
    -0.08
     overwhel
    -0.08
    ƣ
    -0.07
    ﯟ
    -0.07
     İşte
    -0.07
    .ByteString
    -0.07
     שב
    -0.07
     kardeş
    -0.07
     مباراة
    -0.07
    קום
    -0.07
    POSITIVE LOGITS
     southwestern
    0.07
    料
    0.07
    Contract
    0.07
    ом
    0.07
    |,↵
    0.06
    丰
    0.06
    ivi
    0.06
     pub
    0.06
    FirstName
    0.06
    Ju
    0.06
    Activations Density 0.050%

    No Known Activations