© 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. 99144
    Prev
    Next
    INDEX
    Explanations

    first; charter

    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
    亿ä¸ĩ
    -0.29
     Hyp
    -0.27
    lier
    -0.25
    impact
    -0.25
    ichel
    -0.25
    omes
    -0.24
    ame
    -0.24
    ä¼łè¯´
    -0.24
    olution
    -0.24
    帮åĬ©ä¼ģä¸ļ
    -0.24
    POSITIVE LOGITS
    rin
    0.28
    ossier
    0.28
    è¿ĽæĿ¥
    0.27
     routinely
    0.26
    andr
    0.26
    ä½ľä¸ļ
    0.25
     downright
    0.25
    adel
    0.24
    -round
    0.23
    igte
    0.23
    Activations Density 0.006%

    No Known Activations