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. 72515
    Prev
    Next
    INDEX
    Explanations

    Elections

    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
    咄
    -0.08
    .moveToNext
    -0.07
    _coord
    -0.07
     canlı
    -0.06
    assel
    -0.06
     RDF
    -0.06
    太子
    -0.06
    医保
    -0.06
    _att
    -0.06
     darf
    -0.06
    POSITIVE LOGITS
    .onChange
    0.07
    /backend
    0.07
    干部队伍
    0.06
    mx
    0.06
    >`↵
    0.06
     reaction
    0.06
    fabs
    0.06
    ween
    0.06
     simpl
    0.06
     Benchmark
    0.06
    Activations Density 0.018%

    No Known Activations