© 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. 43919
    Prev
    Next
    INDEX
    Explanations

    rankings

    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
    åĩ¡
    -0.28
    äd
    -0.28
    å²Ľ
    -0.27
     insensitive
    -0.27
    loor
    -0.26
    山谷
    -0.26
    è°·
    -0.25
    ä¸ĩå¹³æĸ¹ç±³
    -0.24
     ä
    -0.24
    .TO
    -0.24
    POSITIVE LOGITS
     index
    0.25
    anity
    0.25
    ernity
    0.25
    _crossentropy
    0.25
     Index
    0.24
     Thesis
    0.24
    perf
    0.24
     obscene
    0.24
     Performing
    0.24
     performance
    0.24
    Activations Density 0.002%

    No Known Activations