© 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. 22200
    Prev
    Next
    INDEX
    Explanations

    hexagonal lattice structures

    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
    Scoped
    -0.08
    åĮ¡
    -0.08
     litt
    -0.07
    å·¦åı³çļĦ
    -0.07
    lettes
    -0.07
    INLINE
    -0.07
     Stall
    -0.07
    _tunnel
    -0.07
    åı£
    -0.07
    æĿł
    -0.07
    POSITIVE LOGITS
    æ¯ıéļĶ
    0.09
     regelmÃ¤ÃŁ
    0.08
     regular
    0.07
    ç½ijæł¼
    0.07
     geomet
    0.07
    åĽ¾æ¡Ī
    0.07
    è§Ħå¾ĭ
    0.07
    è¦ıå¾ĭ
    0.07
    regular
    0.07
     symmetry
    0.07
    Activations Density 0.002%

    No Known Activations