© 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. 107712
    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
     interstate
    -0.27
    æ¿Ĥ
    -0.26
    å¼łå®¶
    -0.25
     ká»ĭp
    -0.24
     fier
    -0.24
     afr
    -0.24
    adem
    -0.23
    atham
    -0.23
    .mas
    -0.23
     swinger
    -0.23
    POSITIVE LOGITS
    éĢĢ
    0.28
    lay
    0.26
    ä¹IJ趣
    0.26
    ä¹³
    0.26
     recess
    0.25
    ä¹IJ
    0.25
    两人
    0.23
    cité
    0.23
    lab
    0.23
    åĽ¾çīĩæĿ¥æºIJ
    0.23
    Activations Density 2.943%

    No Known Activations

    This feature has no known activations.