© 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. 20-TRANSCODER-HP
    7. 129706
    Prev
    Next
    INDEX
    Explanations

    clear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    说çĿĢ
    -0.28
    antz
    -0.26
     Forever
    -0.26
    åºľ
    -0.25
    åĩºå¢ĥ
    -0.25
    èģĶç³»æĪij们
    -0.25
     borderline
    -0.24
     tÆ°á»Łng
    -0.24
    nite
    -0.24
    FACE
    -0.24
    POSITIVE LOGITS
    éĥ½åĸľæ¬¢
    0.26
    æ¼ł
    0.26
      ↵    ↵
    0.26
    isko
    0.25
    {{{
    0.25
    èĥ½åĬĽå¼º
    0.25
    .vol
    0.24
    éĴ©
    0.23
     ActivityCompat
    0.23
    ${
    0.23
    Activations Density 9.832%

    No Known Activations