© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 62906
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
    åı£ä¸Ń
    -0.28
    organ
    -0.27
    çı¥
    -0.26
    ombat
    -0.26
    .realm
    -0.25
    èľİ
    -0.24
    ï·º
    -0.24
     lineWidth
    -0.24
    请æĤ¨
    -0.24
    att
    -0.23
    POSITIVE LOGITS
    pector
    0.29
    ikit
    0.27
    piring
    0.26
    bate
    0.26
    cam
    0.26
    Bs
    0.26
    ä¸İæŶ
    0.25
    BW
    0.25
     lacking
    0.24
    éĶĻ
    0.24
    Activations Density 3.752%

    No Known Activations