© 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. 87180
    Prev
    Next
    INDEX
    Explanations

    quantity

    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
    æĪĸèĢħåħ¶ä»ĸ
    -0.28
     round
    -0.28
    vest
    -0.28
    æĸ¥
    -0.26
    æĪĸèĢħ
    -0.26
    éĽĨ群
    -0.25
    ãģ«åĩº
    -0.25
    ä¹łæĥ¯äºĨ
    -0.24
    .online
    -0.24
    æľīæĿĥ
    -0.24
    POSITIVE LOGITS
    été
    0.28
    tring
    0.27
     newcom
    0.27
    çļĦæł·åŃIJ
    0.26
    >null
    0.26
    ÑģÑĤвеннÑĭе
    0.26
    QUI
    0.25
    èŀĤ
    0.25
    nox
    0.25
    :↵↵↵↵↵↵
    0.24
    Activations Density 0.012%

    No Known Activations