© 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. 87940
    Prev
    Next
    INDEX
    Explanations

    Google-related technical content

    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
    æİ¥åıĹ
    -0.27
    DrawerToggle
    -0.26
    åľ¨æİ¥åıĹ
    -0.26
    andom
    -0.25
    _wheel
    -0.25
    æĪIJåĪĨ
    -0.24
    goto
    -0.24
     Ting
    -0.24
    avar
    -0.24
    GGLE
    -0.24
    POSITIVE LOGITS
    èĢĮçİ°åľ¨
    0.29
    erro
    0.28
     (`
    0.26
    å®ģåİ¿
    0.25
    æĪijè¿ĺæĺ¯
    0.25
    çīĪæĿĥå½Ĵ
    0.25
    çļĦè¯Ŀ
    0.25
    itional
    0.23
    å»ºåĽ½
    0.23
    åİŁæĸĩåľ°åĿĢ
    0.23
    Activations Density 0.007%

    No Known Activations