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. 130225
    Prev
    Next
    INDEX
    Explanations

    and

    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
    igua
    -0.26
     Suzanne
    -0.26
    ä¿¡æģ¯æľįåĬ¡
    -0.26
    æ¶µ
    -0.25
    atis
    -0.25
    ince
    -0.24
    [random
    -0.24
    ctal
    -0.24
    é¦ĸ次
    -0.24
    orp
    -0.23
    POSITIVE LOGITS
    è£ķ
    0.31
    ä¾µçķ¥
    0.27
    coal
    0.26
    zes
    0.25
    循
    0.25
    ç¥Ľ
    0.25
    å¾Ī大çļĦ
    0.24
     theoretical
    0.24
     Myers
    0.24
    Queryable
    0.23
    Activations Density 0.019%

    No Known Activations