© 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. 30-TRANSCODER-HP
    7. 97080
    Prev
    Next
    INDEX
    Explanations

    APIs and signup

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĩĨ
    -0.26
    onica
    -0.23
    esser
    -0.23
    æĿĤ
    -0.23
    lected
    -0.23
    \CMS
    -0.23
     pier
    -0.23
    ãĥŀãĥ¼
    -0.23
     stores
    -0.23
     cli
    -0.23
    POSITIVE LOGITS
    ç»ıèIJ¥æ´»åĬ¨
    0.26
    flags
    0.26
    _activation
    0.26
    invoke
    0.25
    åļı
    0.25
     Ged
    0.24
    _FLAG
    0.24
    åĬ¡
    0.24
    泡泡
    0.24
    æ¿Ģæ´»
    0.24
    Activations Density 0.004%

    No Known Activations