© 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. 40802
    Prev
    Next
    INDEX
    Explanations

    in

    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
    æĢ»
    -0.27
     total
    -0.26
    total
    -0.26
    azaar
    -0.26
    agged
    -0.25
    .Total
    -0.25
     ~~
    -0.24
    .total
    -0.24
    (total
    -0.24
    á»ĭa
    -0.24
    POSITIVE LOGITS
     real
    0.37
    Real
    0.34
     Real
    0.33
    .real
    0.30
    -real
    0.30
    (real
    0.29
     life
    0.28
    ez
    0.28
    real
    0.28
     REAL
    0.27
    Activations Density 0.002%

    No Known Activations