© 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. 39886
    Prev
    Next
    INDEX
    Explanations

    quaternion algebras, quadratic twists, reflections, rotor

    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
    venuto
    -0.08
     pât
    -0.08
    ätz
    -0.07
    æµģ
    -0.07
    ISED
    -0.07
    STREAM
    -0.07
    ียว
    -0.07
     inoc
    -0.07
    æ±Ĥç²¾
    -0.07
    ä¸İç»´ä¿®
    -0.07
    POSITIVE LOGITS
    ç¿»
    0.08
    蹦
    0.07
     toggle
    0.07
    otton
    0.07
    cest
    0.07
    öv
    0.07
    cheon
    0.07
    Dic
    0.07
    othy
    0.07
    è·³
    0.07
    Activations Density 0.008%

    No Known Activations