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. 146099
    Prev
    Next
    INDEX
    Explanations

    punctuation/symbols

    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
     idols
    -0.29
    llib
    -0.27
     freshness
    -0.26
    fresh
    -0.26
    ecast
    -0.25
    è¿Ļ个åIJįåŃĹ
    -0.25
     obscene
    -0.24
    cba
    -0.24
     unstoppable
    -0.24
    %c
    -0.24
    POSITIVE LOGITS
    aml
    0.30
    [↵
    0.25
    éģĵçIJĨ
    0.25
     Tek
    0.24
    ÄĻ
    0.24
     TECH
    0.24
     "),↵
    0.24
     fusion
    0.24
     [#
    0.24
     Select
    0.23
    Activations Density 0.605%

    No Known Activations