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. 130766
    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
    精准扶贫
    -0.07
    acob
    -0.07
    小型
    -0.07
    ationToken
    -0.07
    ExecutionContext
    -0.07
    探寻
    -0.07
    核查
    -0.07
     maneuvers
    -0.07
    清理
    -0.06
    山庄
    -0.06
    POSITIVE LOGITS
    Dia
    0.08
     CIS
    0.08
    (G
    0.07
     وج
    0.07
    Description
    0.07
     стор
    0.07
    .source
    0.07
    harga
    0.07
     wur
    0.07
    יגה
    0.07
    Activations Density 0.002%

    No Known Activations