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. 46422
    Prev
    Next
    INDEX
    Explanations

    scientific, technical topics

    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
    èģļ
    -0.28
    ÐŁÐ¾Ð´ÑĢоб
    -0.25
    èģĶç³»æĸ¹å¼ı
    -0.25
     Insurance
    -0.25
    æĪIJåIJį
    -0.25
    ÎĪ
    -0.24
    äºĴéĢļ
    -0.24
    çŀĢ
    -0.24
    éķ¿å¯¿
    -0.24
     entert
    -0.24
    POSITIVE LOGITS
     conscious
    0.29
    æ¾Ħ
    0.27
    å¿ĥæĥ³
    0.26
     poison
    0.25
    ephy
    0.25
    asily
    0.25
    ,NULL
    0.25
    á»Ļi
    0.24
    è·Łå¥¹
    0.24
    .utf
    0.24
    Activations Density 0.024%

    No Known Activations