Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 46408
    Prev
    Next
    INDEX
    Explanations

    socket

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨ²
    -0.31
    ç¿»
    -0.30
    Det
    -0.28
    åİŁèijĹ
    -0.28
     det
    -0.28
    det
    -0.27
    åıį转
    -0.27
     occup
    -0.26
     Det
    -0.26
     dét
    -0.25
    POSITIVE LOGITS
    thumbs
    0.33
    æµ·éĩı
    0.28
     granite
    0.28
    æ´¾åĩº
    0.27
    交æİ¥
    0.27
     Parallel
    0.26
    storeId
    0.25
     grids
    0.25
    .axes
    0.25
    æ¯ıå¹´éĥ½
    0.25
    Activations Density 0.024%

    No Known Activations