© 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. 31-TRANSCODER-HP
    7. 17740
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èµ°
    -0.29
    佬
    -0.28
    erable
    -0.26
    åŁ¹åħ»
    -0.26
    anova
    -0.26
    å¤įæĿĤ
    -0.26
    erah
    -0.25
    erator
    -0.25
    uset
    -0.25
     Complex
    -0.25
    POSITIVE LOGITS
    sty
    0.26
    浪
    0.26
     folded
    0.24
    din
    0.24
    åħ¼èģĮ
    0.23
    ä¸ŃåIJ«æľī
    0.23
    亲åŃIJ
    0.23
    æĮĤ
    0.23
    åºĬ
    0.23
    éĢļçĶ¨
    0.23
    Activations Density 0.232%

    No Known Activations