© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11114
    Prev
    Next
    INDEX
    Explanations

    slit and slot openings

    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
    循çĴ°
    -0.09
    åĭ¾
    -0.08
    _cycle
    -0.08
    ÑģÑĤавка
    -0.07
    erv
    -0.07
     flott
    -0.07
    æ²īæµ®
    -0.07
    大å®Ĺ
    -0.07
    æłijä¸Ĭ
    -0.07
    åİŁåľ°
    -0.07
    POSITIVE LOGITS
    宽度
    0.10
     width
    0.09
     widths
    0.09
     slit
    0.09
    宽
    0.08
    宽çļĦ
    0.08
    æĶ¾è¡Į
    0.08
     aperture
    0.08
    -width
    0.08
    æĮ¡æĿ¿
    0.08
    Activations Density 0.005%

    No Known Activations