© 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. 64212
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ´Ĺ
    -0.26
    /Runtime
    -0.26
     meis
    -0.26
    oler
    -0.25
    inan
    -0.24
    .Instance
    -0.24
    /fa
    -0.23
    lar
    -0.23
    lust
    -0.23
    çľ¼
    -0.23
    POSITIVE LOGITS
    tml
    0.27
    à¸Ľà¸£à¸°à¸ªà¸ĩ
    0.27
     orig
    0.27
    encial
    0.26
    ä½ĵèĤ²åľº
    0.26
     frag
    0.26
     souls
    0.25
    azen
    0.25
    æ¯ĽåŃĶ
    0.25
    getCell
    0.25
    Activations Density 1.393%

    No Known Activations

    This feature has no known activations.