© 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. 88996
    Prev
    Next
    INDEX
    Explanations

    applications and abbreviations

    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
    >Show
    -0.29
    aal
    -0.29
     Gord
    -0.28
    Virgin
    -0.28
    æĸĩåĮĸåĴĮ
    -0.27
    dbuf
    -0.27
    ä¸įå¿į
    -0.26
    رÙĪÙģ
    -0.25
    åħĪæĺ¯
    -0.25
    ÐIJÐŀ
    -0.25
    POSITIVE LOGITS
    ientes
    0.28
    ce
    0.26
    uls
    0.25
    _HS
    0.24
    yz
    0.23
    Cog
    0.23
    xes
    0.23
    igh
    0.23
    wen
    0.23
    èŃ
    0.23
    Activations Density 0.003%

    No Known Activations