© 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. 7858
    Prev
    Next
    INDEX
    Explanations

    above or top

    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
    å·¦ä¸ĭè§Ĵ
    -0.08
    éĶµ
    -0.08
    çļĦ大海
    -0.08
    æİ¥åľ°
    -0.07
    iners
    -0.07
    èĤłçĤİ
    -0.07
    jsc
    -0.07
     grounding
    -0.07
    éĵ¿
    -0.07
    å°ıåŃIJ
    -0.07
    POSITIVE LOGITS
     above
    0.13
    太é«ĺ
    0.12
    above
    0.12
    веÑĢÑħ
    0.12
    è¶Ĭé«ĺ
    0.11
     ABOVE
    0.11
    æľĢé«ĺçļĦ
    0.11
     Above
    0.11
    top
    0.11
    /top
    0.11
    Activations Density 0.309%

    No Known Activations