© 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. 42515
    Prev
    Next
    INDEX
    Explanations

    scientific/technical jargon

    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
    寸
    -0.32
    urus
    -0.29
    Uid
    -0.26
    zen
    -0.25
    Sci
    -0.24
     hor
    -0.24
    T
    -0.24
    jar
    -0.24
    DDS
    -0.24
    chas
    -0.24
    POSITIVE LOGITS
     Auf
    0.26
    Invariant
    0.26
    ä¸įåIJĥ
    0.24
    @endif
    0.23
    æ¯Ļ
    0.23
     chù
    0.23
    laden
    0.23
     spanish
    0.23
    ility
    0.23
    eness
    0.22
    Activations Density 0.003%

    No Known Activations