© 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. 27-TRANSCODER-HP
    7. 58598
    Prev
    Next
    INDEX
    Explanations

    Medical and anatomical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¤ļ人
    -0.27
     ÐľÐ¾
    -0.27
    /card
    -0.27
     outs
    -0.27
    uth
    -0.27
    æĭĬ
    -0.26
    çĹĩçĬ¶
    -0.26
    çĻ½äºij
    -0.25
    å±Ĥåĩº
    -0.25
     council
    -0.24
    POSITIVE LOGITS
    åIJijä¸Ĭ
    0.32
    åIJijä¸ĭ
    0.29
     downward
    0.27
    ible
    0.26
    ient
    0.25
    è§ī
    0.25
    odzi
    0.25
    ilent
    0.25
     intervening
    0.25
     silent
    0.25
    Activations Density 0.003%

    No Known Activations