© 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. 86991
    Prev
    Next
    INDEX
    Explanations

    of, in, for

    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
     forb
    -0.29
    “For
    -0.28
    isser
    -0.28
    UDA
    -0.28
     such
    -0.26
     universal
    -0.26
    æı´åĬ©
    -0.25
    á»ī
    -0.25
    such
    -0.24
     Scalars
    -0.24
    POSITIVE LOGITS
    opi
    0.27
    ↵                    ↵
    0.27
    æĸ°éĹ»ç½ij
    0.27
     дог
    0.26
     caul
    0.25
    çļĦèĥĮåIJİ
    0.25
    story
    0.25
    åįĸç»Ļ
    0.24
    çļĦä¸ĢéĿ¢
    0.24
    å¼Ģåĩº
    0.24
    Activations Density 0.012%

    No Known Activations