© 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. 17880
    Prev
    Next
    INDEX
    Explanations

    Code, software, languages

    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
     Halo
    -0.29
    çªģåĩº
    -0.27
     halo
    -0.27
    emens
    -0.26
    åı
    -0.26
    å¼ı
    -0.26
    å´©
    -0.26
    пÑĢоÑģ
    -0.25
    æŀĦ
    -0.25
    utor
    -0.25
    POSITIVE LOGITS
    mour
    0.30
    adi
    0.26
    .sys
    0.26
     SIG
    0.25
    adio
    0.25
    ä½ĵä¼ļ
    0.24
    evice
    0.24
    alité
    0.23
    (mt
    0.23
    æĿĢ
    0.23
    Activations Density 5.491%

    No Known Activations