© 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. 40822
    Prev
    Next
    INDEX
    Explanations

    Linux code and filepaths

    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
     boot
    -0.34
    boot
    -0.33
     Boot
    -0.29
     BOOT
    -0.28
    -images
    -0.28
    entina
    -0.27
    Boot
    -0.27
    BOOT
    -0.26
    æ¼Ĥ
    -0.26
    åį¡å°Ķ
    -0.26
    POSITIVE LOGITS
    ities
    0.28
    ered
    0.28
    usch
    0.27
    çĭł
    0.25
    de
    0.25
    itol
    0.25
    ity
    0.25
    idad
    0.25
    ergarten
    0.25
    _buffer
    0.24
    Activations Density 0.053%

    No Known Activations