© 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. 63840
    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
     unlocks
    -0.28
    ç¢Ł
    -0.27
     sift
    -0.25
    æ¼±
    -0.24
     Dist
    -0.24
     пов
    -0.24
     wink
    -0.23
     Ñĥме
    -0.23
    ç¿»
    -0.23
     stitch
    -0.23
    POSITIVE LOGITS
    emble
    0.27
    ä¿Ŀè¯ģéĩij
    0.26
    ymb
    0.26
    angible
    0.26
     varargin
    0.26
    çł£
    0.26
    ##_
    0.24
    ebra
    0.24
    .dropout
    0.24
     EdgeInsets
    0.24
    Activations Density 6.478%

    No Known Activations

    This feature has no known activations.