© 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. 108197
    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
    ibel
    -0.29
    idor
    -0.28
     thanked
    -0.27
     such
    -0.25
    åĪĨå¼Ģ
    -0.24
     SUCH
    -0.24
    Nonce
    -0.24
    ([(
    -0.24
     Gall
    -0.23
    ipay
    -0.23
    POSITIVE LOGITS
    fts
    0.29
    ä¹±
    0.25
    è¿ĻæĶ¯
    0.25
     Consortium
    0.25
    ogh
    0.25
    象
    0.24
    integr
    0.24
     ÐŁÐµÑĤÑĢ
    0.23
    lyph
    0.23
     Largest
    0.23
    Activations Density 74.337%

    No Known Activations

    This feature has no known activations.