© 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. 87405
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and titles

    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
     delt
    -0.30
    è¶ĭåIJij
    -0.29
    è¦ģç´§
    -0.27
    ctal
    -0.25
    æĺ¨æĹ¥
    -0.24
     ranged
    -0.24
    çīĪæĿĥå½Ĵ
    -0.24
    ÑģÑĤоÑı
    -0.24
    -caret
    -0.24
    imid
    -0.24
    POSITIVE LOGITS
     Ign
    0.29
    powers
    0.27
     knight
    0.26
    _
    0.25
    \_
    0.25
    å©Ĩ
    0.25
    Unicode
    0.24
    enna
    0.24
     pov
    0.24
     deposits
    0.24
    Activations Density 0.006%

    No Known Activations