© 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. 29583
    Prev
    Next
    INDEX
    Explanations

    transforming or processing

    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
    FromClass
    -0.10
     impun
    -0.09
    ypy
    -0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
    WITHOUT
    -0.08
    werker
    -0.08
    .statusText
    -0.08
    æľªç»ıæİĪæĿĥ
    -0.08
    æ¯ħ
    -0.08
    باء
    -0.08
    POSITIVE LOGITS
    并ç»ı
    0.08
    åIJİè¿Ľè¡Į
    0.08
    并éĩį
    0.08
    确认åIJİ
    0.08
    åIJİ
    0.08
    ly
    0.07
    使åħ¶
    0.07
    åIJİåį³åı¯
    0.07
    ally
    0.07
    æĪĸ缴æİ¥
    0.07
    Activations Density 0.022%

    No Known Activations