© 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. 58568
    Prev
    Next
    INDEX
    Explanations

    handling and operators

    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
    æ°´åľŁ
    -0.08
    åĪ°åĮĹ京
    -0.07
    åľ¨æŁIJ
    -0.07
    äºİäºĭ
    -0.07
    setDefault
    -0.07
    循
    -0.07
    åĬ¿å¤´
    -0.07
    öll
    -0.07
    ζί
    -0.07
    麦èĬ½
    -0.07
    POSITIVE LOGITS
     safely
    0.13
    å®īåħ¨çļĦ
    0.11
     безопаÑģно
    0.10
     safer
    0.10
    æĵįä½ľ
    0.10
    å®īåħ¨
    0.10
     saf
    0.10
    ä¸Ģæīĭ
    0.10
    å®īåħ¨éĺ²æĬ¤
    0.09
    å·¥åħ·
    0.09
    Activations Density 0.147%

    No Known Activations