© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 43875
    Prev
    Next
    INDEX
    Explanations

    Technical documents/support forums

    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
    ä¹IJ
    -0.29
    ös
    -0.26
     ST
    -0.26
    æģ³
    -0.26
    RE
    -0.25
     motions
    -0.25
    ST
    -0.24
    ([&
    -0.24
    e
    -0.24
    æ¨Ĥ
    -0.23
    POSITIVE LOGITS
    æľ¬äºº
    0.35
    æľ¬èº«çļĦ
    0.31
    ITED
    0.28
    qty
    0.28
    å¾Ī大
    0.27
    宽
    0.27
    æķ¸
    0.27
    ä¸įåIJĮçļĦ
    0.27
    kah
    0.26
    ä¸įåIJĮ
    0.26
    Activations Density 0.000%

    No Known Activations