© 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. 97253
    Prev
    Next
    INDEX
    Explanations

    Years and dates

    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
    acci
    -0.29
    ucher
    -0.27
    adel
    -0.27
    æĿ±è¥¿
    -0.26
    führer
    -0.26
    诱人
    -0.25
    çļĦæķĪæŀľ
    -0.25
    åĥħ
    -0.25
    eliness
    -0.24
    åĭģ
    -0.24
    POSITIVE LOGITS
    è¿ĩ渡
    0.28
    -best
    0.25
     Ga
    0.25
     Regulatory
    0.24
    å¼Ģå§ĭäºĨ
    0.24
    ä¹ĭ称
    0.24
    Pa
    0.24
    IK
    0.24
     creeping
    0.24
    >Lorem
    0.23
    Activations Density 0.003%

    No Known Activations