© 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. 1073
    Prev
    Next
    INDEX
    Explanations

    toggle, alternating, odd, -1 or 1

    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
    -lang
    -0.07
    erna
    -0.07
     oprav
    -0.07
    LY
    -0.07
    æĩĴ
    -0.07
    æµģæ°´
    -0.07
    ersey
    -0.07
    ä¸ĭæ°´
    -0.07
    æ±Ĥç²¾
    -0.07
     láng
    -0.07
    POSITIVE LOGITS
     togg
    0.09
     toggle
    0.08
    äº¤æĽ¿
    0.08
     altern
    0.08
     oscill
    0.08
    ç¿»
    0.07
    å¥ĩ
    0.07
     odd
    0.07
    .toggle
    0.07
    交éĶĻ
    0.07
    Activations Density 0.003%

    No Known Activations