© 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. 33-TRANSCODER-HP
    7. 52828
    Prev
    Next
    INDEX
    Explanations

    Medical anatomy and procedures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cams
    -0.31
    lotte
    -0.28
    hand
    -0.25
    cgi
    -0.25
    gages
    -0.25
    GINE
    -0.24
     Camden
    -0.23
    ä¼łçľŁ
    -0.23
    .appspot
    -0.23
     organizational
    -0.23
    POSITIVE LOGITS
    ÙĤد
    0.28
     alo
    0.27
     area
    0.27
    人家
    0.26
     spur
    0.26
    emed
    0.26
    sov
    0.25
    avel
    0.25
    éĵ¸
    0.25
     Dere
    0.25
    Activations Density 0.039%

    No Known Activations