© 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. 17732
    Prev
    Next
    INDEX
    Explanations

    programming and software

    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
    æIJº
    -0.33
     Prop
    -0.28
     Yönet
    -0.28
    æī¿
    -0.27
     Dates
    -0.26
    beros
    -0.25
     Filter
    -0.25
     pumping
    -0.25
    å¤ĦçIJĨ
    -0.25
     Mitch
    -0.24
    POSITIVE LOGITS
    åĦĴ
    0.29
    ç»ıæŁ¥
    0.28
     ~(
    0.27
     Hath
    0.26
    ä»ĸ认为
    0.25
     IService
    0.25
    毡
    0.24
     overflowing
    0.24
    -cols
    0.24
    åĸĩåıŃ
    0.24
    Activations Density 1.404%

    No Known Activations