© 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. 141069
    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
    æł½
    -0.27
    è§ĦåĪĴ建设
    -0.26
    ushi
    -0.26
     Switch
    -0.25
    Ä°N
    -0.25
     condom
    -0.24
    ÐĴидео
    -0.24
    (down
    -0.23
     convenience
    -0.23
    åı¯æݧ
    -0.23
    POSITIVE LOGITS
    gre
    0.31
    usa
    0.31
    -fit
    0.30
    æĢ¥
    0.29
    uese
    0.29
    æ¯ı个人éĥ½
    0.28
     escort
    0.28
    ç»
    0.28
     MAD
    0.26
    eric
    0.25
    Activations Density 3.495%

    No Known Activations

    This feature has no known activations.