© 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. 63238
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    çĪ¹
    -0.06
     nuances
    -0.06
     nu
    -0.06
    å¾Ĺ天çĭ¬
    -0.06
    anken
    -0.06
     ‘
    -0.06
    çĻŀ
    -0.06
    æ¯įåŃIJ
    -0.06
    .Errors
    -0.06
    é¦ĸåħĪæĺ¯
    -0.06
    POSITIVE LOGITS
    è¿ŀäºij
    0.08
    reiro
    0.08
    è¾ĵåįµ
    0.07
    继
    0.07
    -Identifier
    0.07
    ç¹¼
    0.07
     ofs
    0.07
    çĽ¸ä¿¡åľ¨
    0.07
    )./
    0.07
    uctions
    0.07
    Activations Density 0.000%

    No Known Activations