© 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. 31-TRANSCODER-HP
    7. 18809
    Prev
    Next
    INDEX
    Explanations

    code/configurations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coes
    -0.29
    .getOwnPropertyDescriptor
    -0.25
     Decomp
    -0.25
     Buffered
    -0.25
    æĸ°åħ´äº§ä¸ļ
    -0.24
    社ç§ij
    -0.24
    oct
    -0.24
    èĩªå®¶
    -0.24
    tant
    -0.23
    太太
    -0.23
    POSITIVE LOGITS
    ç®Ĺ
    0.28
    游
    0.27
    å¹»
    0.27
    æ¼Ĥ
    0.27
    èĻļ
    0.27
    hausen
    0.27
    ield
    0.26
    ç«Ļåľ¨
    0.26
    hell
    0.26
    ields
    0.25
    Activations Density 2.002%

    No Known Activations