© 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. 42791
    Prev
    Next
    INDEX
    Explanations

    structure and geometry

    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
     scientifically
    -0.06
     hoÃłi
    -0.06
    æݺ
    -0.06
     اÙĦÙģض
    -0.06
    èĮĥåĽ´
    -0.06
    isha
    -0.06
    çļĦåģļæ³ķ
    -0.06
    ëve
    -0.06
     utr
    -0.06
    chel
    -0.06
    POSITIVE LOGITS
     symmetry
    0.11
     structure
    0.10
     geometry
    0.09
    ç»Ħç»ĩç»ĵæŀĦ
    0.09
    ç»ĵæŀĦä¸İ
    0.09
    sym
    0.09
    geometry
    0.09
     structures
    0.09
    ç»ĵæŀĦåĴĮ
    0.09
    structure
    0.08
    Activations Density 0.012%

    No Known Activations