© 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. 108067
    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
    #{
    -0.27
     diluted
    -0.27
    ç§ijçłĶ
    -0.27
     cloak
    -0.25
     Summers
    -0.25
    éĻ¢éĻ¢å£«
    -0.25
    å¹³æĸ¹åħ¬éĩĮ
    -0.24
    èĵ¿
    -0.24
    æĹ·
    -0.24
    åĩºåİĤ
    -0.24
    POSITIVE LOGITS
    æŃ£æĸĩ
    0.28
     Businesses
    0.27
    ooth
    0.27
     Boxes
    0.27
    -heart
    0.26
    书ä¸Ń
    0.25
    LOCATION
    0.25
    books
    0.25
     Hearth
    0.25
    (embed
    0.24
    Activations Density 44.169%

    No Known Activations

    This feature has no known activations.