© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16815
    Prev
    Next
    INDEX
    Explanations

    information not disclosed or missing

    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
    åºĶè¿IJ
    -0.07
    ezo
    -0.07
    åĬ¨ä¸įåĬ¨
    -0.07
    æĢĿç»´çļĦ
    -0.07
    opyright
    -0.07
    åŃļ
    -0.07
    иÑĤе
    -0.06
    uba
    -0.06
    uga
    -0.06
    /disable
    -0.06
    POSITIVE LOGITS
    åħ·ä½ĵ
    0.08
    ç¬
    0.07
    æľ¬æĹ¥
    0.07
    åħ·ä½ĵåĨħ容
    0.07
     generic
    0.07
    åħ·é«Ķ
    0.07
    idd
    0.07
     concrete
    0.07
    ised
    0.06
    rud
    0.06
    Activations Density 0.091%

    No Known Activations