© 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. 33-TRANSCODER-HP
    7. 54554
    Prev
    Next
    INDEX
    Explanations

    involve

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ,âĢ¦↵↵
    -0.45
    ä»ĸä»¬åľ¨
    -0.43
    –and
    -0.43
    ä»ĸ们æĺ¯
    -0.42
    ä»ĸ们
    -0.41
     они
    -0.40
    ä»ĸåĢij
    -0.39
    they
    -0.38
    åĽłä¸ºä»ĸ们
    -0.38
    They
    -0.38
    POSITIVE LOGITS
     few
    0.46
     strong
    0.42
     some
    0.41
     extensive
    0.41
    0.41
     complex
    0.40
     the
    0.39
     intense
    0.39
     people
    0.38
     profound
    0.38
    Activations Density 0.026%

    No Known Activations