© 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. 45643
    Prev
    Next
    INDEX
    Explanations

    algebraic group theory

    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
    d
    -0.07
    b
    -0.07
    液
    -0.07
    f
    -0.07
    z
    -0.06
    ë§Ŀ
    -0.06
    list
    -0.06
    çº¢ç´ł
    -0.06
    涯
    -0.06
    åĪĨ级
    -0.06
    POSITIVE LOGITS
     aspet
    0.08
    åįģä¸īç«ł
    0.08
    ehl
    0.08
    -lite
    0.08
     fatally
    0.08
    æ¯ĵ
    0.08
    emode
    0.08
     rotations
    0.08
    妬
    0.08
    iskon
    0.07
    Activations Density 0.003%

    No Known Activations