© 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. 63428
    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
    estro
    -0.29
     executions
    -0.27
    UBL
    -0.27
    oen
    -0.26
     Ud
    -0.26
     accesses
    -0.25
    _uid
    -0.25
    usch
    -0.25
    .dex
    -0.24
    onomies
    -0.24
    POSITIVE LOGITS
    说æĺİ书
    0.27
    atto
    0.27
    ä¸įéĶĻ
    0.27
     nothing
    0.27
    为导åIJij
    0.26
    ilation
    0.25
    vac
    0.25
    çľŁç©º
    0.25
    æ²ī
    0.25
    åľ£ç»ı
    0.25
    Activations Density 35.863%

    No Known Activations

    This feature has no known activations.