© 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. 18108
    Prev
    Next
    INDEX
    Explanations

    medical procedures and code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    代表
    -0.29
    åıį
    -0.26
    emb
    -0.26
     frank
    -0.25
    æĬĽ
    -0.25
    leh
    -0.25
     maur
    -0.24
    èĥĮä¸Ĭ
    -0.24
     skate
    -0.24
    ä¼łéĢĴ
    -0.24
    POSITIVE LOGITS
     integrating
    0.29
    ÑĤÑĭ
    0.29
    åĻį
    0.28
     cresc
    0.28
    ä¹ĭåĪĿ
    0.28
     Household
    0.28
    å½ĵåĪĿ
    0.27
    Grow
    0.27
     Growth
    0.27
     grew
    0.27
    Activations Density 1.259%

    No Known Activations