© 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. 97154
    Prev
    Next
    INDEX
    Explanations

    your/you

    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
    sis
    -0.28
     competit
    -0.26
    æĪIJåŀĭ
    -0.25
     ÑģебÑı
    -0.24
    ings
    -0.24
    itch
    -0.24
    æĬĬå®ĥ
    -0.24
    stands
    -0.24
    iska
    -0.23
     spl
    -0.23
    POSITIVE LOGITS
    /MPL
    0.29
    gom
    0.28
     Gran
    0.27
    .gstatic
    0.26
    åĪĨæѧ
    0.26
    èĥĸ
    0.25
    æŃ¤æ¬¡
    0.25
    ä¸įç®Ĺ
    0.25
    affected
    0.25
     prer
    0.24
    Activations Density 0.018%

    No Known Activations