© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111989
    Prev
    Next
    INDEX
    Explanations

    technical/scientific topics

    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
    Not in Any Lists

    No Comments

    Negative Logits
    IFI
    -0.31
    entine
    -0.26
    ivet
    -0.26
    artin
    -0.26
    æĹ©æĻ¨
    -0.25
    IFIC
    -0.25
    人åĿĩ
    -0.24
     Cadillac
    -0.24
    prech
    -0.24
    æĪĽ
    -0.24
    POSITIVE LOGITS
    åĴĮæľįåĬ¡
    0.27
     MOST
    0.27
    "struct
    0.24
    è¿Ļ份
    0.23
    éĢ»
    0.23
     _______,
    0.23
     verst
    0.23
     vad
    0.23
     hung
    0.23
     seeming
    0.23
    Activations Density 0.002%

    No Known Activations