© 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. 21176
    Prev
    Next
    INDEX
    Explanations

    dissecting, cedar

    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
    人
    -0.10
    à¸ĩาà¸Ļ
    -0.10
    tır
    -0.10
    ity
    -0.10
    vironment
    -0.09
    ëģĶ
    -0.09
    ation
    -0.09
    æľīæĸ°çļĦ
    -0.09
    ä¸įç´Ĭ
    -0.09
    æľīçĶŁ
    -0.08
    POSITIVE LOGITS
    ا
    0.26
    a
    0.25
    ly
    0.21
    а
    0.20
    缸è¾ħ缸æĪIJ
    0.19
    er
    0.18
    ा
    0.18
    ÑģÑĮ
    0.17
    jenigen
    0.16
    า
    0.16
    Activations Density 3.255%

    No Known Activations