© 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. 25-TRANSCODER-HP
    7. 107172
    Prev
    Next
    INDEX
    Explanations

    Medical/pharmaceutical context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    樣
    -0.30
    åıĭè°Ĭ
    -0.29
    spoken
    -0.25
    .rectangle
    -0.25
    侥幸
    -0.25
    aster
    -0.25
    ä¸Ģåı£
    -0.24
    INES
    -0.24
    æł·
    -0.24
    æł·çļĦ
    -0.24
    POSITIVE LOGITS
    ebile
    0.26
    itals
    0.26
    ä¸ĵçĶ¨
    0.25
     dati
    0.24
     mnemonic
    0.24
    AtA
    0.24
     mapping
    0.24
    -scalable
    0.23
    tip
    0.23
    View
    0.23
    Activations Density 1.171%

    No Known Activations