© 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. 97053
    Prev
    Next
    INDEX
    Explanations

    genetics and DNA

    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
    å¾Ļ
    -0.28
    apult
    -0.27
     hud
    -0.27
    ature
    -0.27
     squeezing
    -0.26
     Wald
    -0.26
    ographies
    -0.25
     squeez
    -0.25
    ECH
    -0.24
    olls
    -0.24
    POSITIVE LOGITS
    ä¸Ŀ
    0.29
     nal
    0.28
    tea
    0.26
    loor
    0.26
    inia
    0.25
    __(↵
    0.25
     unanswered
    0.25
    对该
    0.25
     injured
    0.24
    åĪĨ
    0.24
    Activations Density 0.009%

    No Known Activations