© 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. 140980
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    å¹´ä¹ĭä¹ħ
    -0.31
    人éĢī
    -0.28
    ysis
    -0.26
    ledge
    -0.26
    veyor
    -0.25
    kte
    -0.24
    liner
    -0.23
    éķ·æľŁ
    -0.23
    flags
    -0.23
    fen
    -0.23
    POSITIVE LOGITS
    atted
    0.29
    Similar
    0.24
     paras
    0.24
     append
    0.24
    åĨĻçĿĢ
    0.24
     Tips
    0.24
     tip
    0.24
    æŃ£çīĪ
    0.24
    rote
    0.23
     libs
    0.23
    Activations Density 6.625%

    No Known Activations