© 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. 41044
    Prev
    Next
    INDEX
    Explanations

    say "with"

    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
    aming
    -0.26
    urope
    -0.25
    anness
    -0.25
     feud
    -0.24
     pent
    -0.24
    åĶ¯ä¸Ģ
    -0.24
    åĻ¨å®ĺ
    -0.24
    omers
    -0.24
    åķĨåѦéĻ¢
    -0.24
    å·¥ä½ľæĸ¹æ¡Ī
    -0.24
    POSITIVE LOGITS
    asers
    0.29
    acked
    0.28
    charg
    0.26
    escription
    0.26
    è´£ç¼ĸ
    0.25
    .getvalue
    0.25
     wooden
    0.24
    isen
    0.24
    ed
    0.24
    潮湿
    0.23
    Activations Density 0.001%

    No Known Activations