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. 7-TRANSCODER-HP
    4. 130385
    Prev
    Next
    INDEX
    Explanations

    suggestions and indications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cop
    -0.27
    é¨
    -0.26
    erk
    -0.26
    ponible
    -0.26
    proto
    -0.25
    ç»§ç»Ńä¿ĿæĮģ
    -0.25
    pcs
    -0.25
    æĨ©
    -0.25
     prelim
    -0.24
    emon
    -0.24
    POSITIVE LOGITS
    è£ħå¤ĩåζéĢł
    0.29
    ufacturer
    0.29
    ä¸Ģåı¥
    0.25
    èŀºä¸Ŀ
    0.25
    è´¿
    0.25
    éĹ©
    0.25
    èµ°åĩºæĿ¥
    0.24
    manufacturer
    0.24
     ratings
    0.24
    å²³
    0.24
    Activations Density 0.001%

    No Known Activations