© 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. 141849
    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
     Humb
    -0.31
    æĹłåı¯
    -0.29
    à¹Īาย
    -0.29
    verbatim
    -0.25
    åĪĴ
    -0.25
    vi
    -0.24
     unconditional
    -0.24
    NEY
    -0.24
     embar
    -0.24
    Ĥ¬
    -0.24
    POSITIVE LOGITS
    èĹ©
    0.25
    ä¹ĭæīĢ
    0.25
    ç¨įç¨į
    0.24
    uli
    0.24
    æĪķ
    0.24
    :checked
    0.24
     VAN
    0.24
     gore
    0.23
     (*)(
    0.23
    æĿ¥è¿ĻéĩĮ
    0.23
    Activations Density 0.221%

    No Known Activations

    This feature has no known activations.