© 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. 38841
    Prev
    Next
    INDEX
    Explanations

    logging identifiers

    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
    æİĸ
    -0.08
    -ng
    -0.07
    çŃĸ
    -0.07
    ç½Ĺæ±ī
    -0.06
    űr
    -0.06
    luan
    -0.06
    æī¹
    -0.06
     ins
    -0.06
    è°į
    -0.06
    èĥ¡åŃIJ
    -0.06
    POSITIVE LOGITS
    stag
    0.08
    avis
    0.07
    aime
    0.07
    ÑĤино
    0.07
    yi
    0.07
    omo
    0.07
    çļĦéĤ£ä¸ªäºº
    0.07
     asal
    0.07
    æ¼²
    0.07
     Uncategorized
    0.07
    Activations Density 0.183%

    No Known Activations