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. 24610
    Prev
    Next
    INDEX
    Explanations

    include

    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
     fut
    -0.28
    æľ¬èº«å°±æĺ¯
    -0.26
    éģµ
    -0.25
    å±ŀäºİ
    -0.25
    obil
    -0.24
    æľ¬èº«
    -0.24
     jä
    -0.24
    ç«Ļ
    -0.24
    antas
    -0.24
    ä»ĸèĩªå·±
    -0.24
    POSITIVE LOGITS
    aldo
    0.33
    æłĩéħį
    0.29
     anymore
    0.28
    ester
    0.28
    thouse
    0.26
     Bags
    0.25
    [S
    0.25
    .Restr
    0.25
     $_[
    0.24
    ral
    0.24
    Activations Density 0.004%

    No Known Activations