© 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. 98035
    Prev
    Next
    INDEX
    Explanations

    caused

    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
    æľĢå¤ļçļĦ
    -0.30
    çļĦå°±æĺ¯
    -0.28
    çļĦæĸĩç«ł
    -0.28
    èĿĮ
    -0.25
    $/
    -0.25
    å½ĵåĪĿ
    -0.25
     bolt
    -0.25
    енÑĤа
    -0.24
    loth
    -0.24
    ä¼ĺäºİ
    -0.24
    POSITIVE LOGITS
    idos
    0.28
    ennie
    0.27
     ViewData
    0.26
    ophys
    0.25
    à¹Ģà¸Ĺศ
    0.25
    ocrine
    0.24
     interle
    0.24
    ocio
    0.24
     Venus
    0.23
    innen
    0.23
    Activations Density 0.020%

    No Known Activations