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. 130787
    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
    诀
    -0.09
    führen
    -0.07
    allee
    -0.07
    沨
    -0.07
    .getConnection
    -0.06
     настоящ
    -0.06
    eya
    -0.06
    URLException
    -0.06
     conhec
    -0.06
    _rename
    -0.06
    POSITIVE LOGITS
    碾
    0.07
    居家
    0.07
     probabil
    0.07
    sale
    0.07
     Management
    0.07
    ımı
    0.07
     questionnaire
    0.07
     aque
    0.06
     civilization
    0.06
     заказ
    0.06
    Activations Density 0.000%

    No Known Activations