© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130804
    Prev
    Next
    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash
    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
     lift
    -0.28
     gran
    -0.27
    ä¹Ī
    -0.26
    æ´¥
    -0.26
    lift
    -0.25
    lifting
    -0.25
    kaar
    -0.25
     se
    -0.24
    é½IJ
    -0.24
     Lift
    -0.24
    POSITIVE LOGITS
    éļıä¹ĭ
    0.30
    -Nov
    0.29
     Assass
    0.28
    ä¸įåIJĪæł¼
    0.28
    款
    0.26
    èĵij
    0.25
    /Runtime
    0.24
     Killed
    0.24
    /mark
    0.24
    /unit
    0.24
    Activations Density 71.568%

    No Known Activations