© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26736
    Prev
    Next
    INDEX
    Explanations

    Sibling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    axe
    -0.07
    çĶŁçļĦ
    -0.07
    ata
    -0.06
    à¯ģà®ķ
    -0.06
    çĶŁ
    -0.06
    çĽİ
    -0.06
    crement
    -0.06
    iles
    -0.06
    èĹī
    -0.06
    asts
    -0.06
    POSITIVE LOGITS
     cabe
    0.08
    æĬĦæĬ¥
    0.07
     Hort
    0.07
    identally
    0.07
     abort
    0.07
    unaan
    0.07
    ehm
    0.07
    ä¸įè¿ľ
    0.07
    yac
    0.07
    settings
    0.07
    Activations Density 0.003%

    No Known Activations