© 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. 97151
    Prev
    Next
    INDEX
    Explanations

    programming

    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
    æĪĸå¤ļ
    -0.29
    idel
    -0.24
    ì±ķ
    -0.23
    adc
    -0.23
     charms
    -0.23
    dealloc
    -0.23
    æĮĩåIJij
    -0.22
    irable
    -0.22
     recurs
    -0.22
    acles
    -0.22
    POSITIVE LOGITS
     certain
    0.27
    夷
    0.26
    ä¸Ģå®ļçļĦ
    0.25
    çļĦåIJĮåѦ
    0.24
    èĥ¡
    0.24
    ful
    0.24
     luôn
    0.23
    ç»Ī究
    0.23
     unfolding
    0.23
    æıIJ
    0.23
    Activations Density 0.034%

    No Known Activations