© 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. 32-TRANSCODER-HP
    7. 43352
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    most
    -0.44
     most
    -0.42
    Most
    -0.37
     Most
    -0.36
    ä¸ŃæľĢ
    -0.35
    -most
    -0.35
    MOST
    -0.35
     MOST
    -0.34
    _most
    -0.33
    æľĢæľī
    -0.33
    POSITIVE LOGITS
     a
    0.46
     new
    0.44
    ä¸Ģ个æĸ°çļĦ
    0.43
    ä½ľä¸ºä¸Ģ个
    0.41
    æĸ°
    0.41
    ä¸Ģ个
    0.39
    æĸ°çļĦ
    0.37
     as
    0.37
    new
    0.36
    æĺ¯ä¸Ģ个
    0.34
    Activations Density 0.001%

    No Known Activations