© 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. 22-TRANSCODER-HP
    7. 110932
    Prev
    Next
    INDEX
    Explanations

    medical history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     initialised
    -0.30
     mid
    -0.27
     initializing
    -0.26
     overnight
    -0.26
     incumb
    -0.25
     recal
    -0.25
     upfront
    -0.25
    rompt
    -0.25
    initializer
    -0.24
     initially
    -0.24
    POSITIVE LOGITS
     зло
    0.29
    ç¾İ好
    0.26
    ilter
    0.26
     adversity
    0.26
     corner
    0.25
    à¸Ńà¸ģ
    0.25
    bei
    0.24
    iram
    0.24
    xAD
    0.24
    èĬ±çº¹
    0.23
    Activations Density 0.008%

    No Known Activations