© 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. 63503
    Prev
    Next
    INDEX
    Explanations

    ear

    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
    allen
    -0.28
    ety
    -0.28
    inde
    -0.26
     Ham
    -0.26
     Career
    -0.25
    chner
    -0.25
    'im
    -0.24
     Batt
    -0.24
    flies
    -0.24
    ets
    -0.23
    POSITIVE LOGITS
    èĥ¼
    0.29
     disgusted
    0.28
    onor
    0.26
    ä»»ä½ķå½¢å¼ı
    0.25
    º«
    0.25
    æĿ¥åģļ
    0.25
    WritableDatabase
    0.25
    åIJİèĢħ
    0.24
    .nz
    0.24
    å¤įæĿĤçļĦ
    0.24
    Activations Density 13.016%

    No Known Activations