© 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. 64421
    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
     Eid
    -0.28
    ิà¸ĩ
    -0.25
    èĮ¨
    -0.24
    宣
    -0.23
    ToWorld
    -0.23
    çĶŁç´ł
    -0.23
    ognito
    -0.23
    egal
    -0.23
    inger
    -0.23
    槽
    -0.23
    POSITIVE LOGITS
    orks
    0.28
    让åѦçĶŁ
    0.26
    SEA
    0.25
    ihan
    0.24
    è®®
    0.24
    din
    0.24
    st
    0.24
     manh
    0.24
    ä¸Ģæīĭ
    0.23
     conserv
    0.23
    Activations Density 79.380%

    No Known Activations

    This feature has no known activations.