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. 146282
    Prev
    Next
    INDEX
    Explanations

    vendor

    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
     fal
    -0.31
    elpers
    -0.28
    inas
    -0.27
    è´¡çĮ®
    -0.26
     outs
    -0.26
    apis
    -0.26
    uis
    -0.26
    uire
    -0.25
    Helpers
    -0.24
    ilia
    -0.24
    POSITIVE LOGITS
     Unary
    0.28
    æĮĩ导ä¸ĭ
    0.27
    è¢Ħ
    0.25
     môn
    0.25
    åıĺæĢģ
    0.24
    æİ°
    0.24
    票
    0.24
    ROW
    0.24
    ä¸Ĭåīį
    0.24
     unary
    0.23
    Activations Density 0.310%

    No Known Activations