© 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. 88290
    Prev
    Next
    INDEX
    Explanations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĮĩçļĦæĺ¯
    -0.28
    ä¸ĢåĪ»
    -0.27
    便æĺ¯
    -0.26
    .Alpha
    -0.26
     jer
    -0.24
    isible
    -0.24
    æĦ§
    -0.24
    ouver
    -0.24
    çIJIJ
    -0.24
     thủ
    -0.24
    POSITIVE LOGITS
     dotted
    0.28
     Bout
    0.27
    Nib
    0.25
    iÄį
    0.25
     Jehovah
    0.25
    ivate
    0.25
    IRECT
    0.24
    ä¸įä¸Ģå®ļ
    0.24
    Tho
    0.24
    çļĤ
    0.24
    Activations Density 0.028%

    No Known Activations