© 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. 44228
    Prev
    Next
    INDEX
    Explanations

    sharp

    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
    Negative Logits
    å¢ŀåĬł
    -0.95
     increase
    -0.92
     decrease
    -0.88
    increase
    -0.88
    Increase
    -0.88
     Increase
    -0.88
    incre
    -0.87
     Decre
    -0.85
    åĩıå°ij
    -0.84
     increasing
    -0.82
    POSITIVE LOGITS
    apia
    0.28
    /welcome
    0.27
    igraphy
    0.25
    /latest
    0.25
     flyer
    0.24
    SACTION
    0.23
     bubble
    0.23
     uwagÄĻ
    0.23
    /epl
    0.23
    æ¯Ķäºļ
    0.23
    Activations Density 0.001%

    No Known Activations