© 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. 63826
    Prev
    Next
    INDEX
    Explanations

    difference

    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
     levels
    -0.48
    Levels
    -0.48
     varying
    -0.47
    å±Ĥ次
    -0.45
     Levels
    -0.45
    levels
    -0.45
    _levels
    -0.42
    ä¸įåIJĮ
    -0.41
    çŃī级
    -0.41
     unterschied
    -0.39
    POSITIVE LOGITS
    edom
    0.26
    æµ·ä¸Ĭ
    0.26
    ãģĤãģŁãĤĬ
    0.26
    ishi
    0.25
    atted
    0.24
    ida
    0.24
     Reid
    0.23
    edian
    0.23
    æĿ·
    0.23
    ики
    0.23
    Activations Density 46.115%

    No Known Activations