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. 36304
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    oke
    -0.07
    𝒔
    -0.07
    短暂
    -0.07
    /The
    -0.06
    hours
    -0.06
    _req
    -0.06
    -grey
    -0.06
     hẹn
    -0.06
    춘
    -0.06
     davidjl
    -0.06
    POSITIVE LOGITS
     artykuł
    0.07
     motifs
    0.06
    常用
    0.06
     scaler
    0.06
    .equalsIgnoreCase
    0.06
     sâu
    0.06
     authorize
    0.06
    \Db
    0.06
    핳
    0.06
    上がる
    0.06
    Activations Density 0.008%

    No Known Activations