© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108185
    Prev
    Next
    INDEX
    Explanations

    Brend names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bags
    -0.28
    clide
    -0.27
    ->{'
    -0.25
    opia
    -0.25
    rating
    -0.25
    VD
    -0.25
    iator
    -0.24
    frog
    -0.24
    ä¸įç»ı
    -0.24
    plane
    -0.24
    POSITIVE LOGITS
    缩
    0.27
    ä¾ĭ
    0.26
    以æĿ¥
    0.26
    ä¾Ľæļĸ
    0.26
     val
    0.26
    æ¬ºè´Ł
    0.26
    REW
    0.25
    pth
    0.25
     consuming
    0.24
    //!↵
    0.24
    Activations Density 0.144%

    No Known Activations