© 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. 40819
    Prev
    Next
    INDEX
    Explanations

    scientific writing

    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
     INTERVAL
    -0.28
    stakes
    -0.28
     Patt
    -0.28
    æĻŀ
    -0.26
    身åIJİ
    -0.26
     buc
    -0.26
     Serial
    -0.26
    æ¼±
    -0.25
    rade
    -0.25
    â¼ł
    -0.24
    POSITIVE LOGITS
     with
    0.37
     carrying
    0.34
     composed
    0.34
     produced
    0.33
     formed
    0.33
     falling
    0.32
     made
    0.31
     experiencing
    0.30
    .compose
    0.30
     held
    0.29
    Activations Density 0.005%

    No Known Activations