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. 27-TRANSCODER-HP
    4. 1079
    Prev
    Next
    INDEX
    Explanations

    technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĢĿ绪
    -0.27
    .shtml
    -0.27
    safe
    -0.26
     safety
    -0.26
     warped
    -0.25
    ately
    -0.25
    念
    -0.25
    afe
    -0.25
    etus
    -0.24
     tq
    -0.24
    POSITIVE LOGITS
    èįļ
    0.33
    åĬ¨æľº
    0.26
    /cms
    0.26
     Candle
    0.25
    chsel
    0.24
    éħª
    0.24
    offer
    0.24
    acular
    0.24
    trial
    0.23
    Jos
    0.23
    Activations Density 0.002%

    No Known Activations