© 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. 107651
    Prev
    Next
    INDEX
    Explanations

    sunny weather

    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
    lessly
    -0.29
     troch
    -0.25
     Inherits
    -0.25
    ä¸įå¿į
    -0.25
    .nb
    -0.25
    _origin
    -0.24
    lays
    -0.24
     luaL
    -0.24
    tsy
    -0.24
    ick
    -0.24
    POSITIVE LOGITS
    段
    0.30
    Scaler
    0.29
     Dil
    0.25
    å®Į
    0.25
     scal
    0.25
    ç»Ħç»ĩé¢Ĩ导
    0.25
    ç¨Ģ
    0.24
    scal
    0.24
     Afr
    0.24
    gio
    0.24
    Activations Density 2.992%

    No Known Activations