© 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. 107253
    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
    kaar
    -0.25
    Ñĥни
    -0.25
    yat
    -0.24
     Terminal
    -0.24
    ä»Ģä¹Īéĥ½ä¸į
    -0.24
     lit
    -0.24
    æ·Ģ
    -0.24
    HEET
    -0.24
    [assembly
    -0.23
    (train
    -0.23
    POSITIVE LOGITS
    ctors
    0.27
    amespace
    0.27
    åħ¥åħļ
    0.26
     —
    0.25
     ++)
    0.24
    _normalized
    0.24
    该项
    0.24
    Orth
    0.24
    Dirs
    0.23
     поб
    0.23
    Activations Density 1.890%

    No Known Activations

    This feature has no known activations.