© 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. 17806
    Prev
    Next
    INDEX
    Explanations

    legal citations and case names

    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
    вл
    -0.08
    ulario
    -0.07
     Präsent
    -0.07
    .reader
    -0.07
    lene
    -0.07
    秫
    -0.07
    ä¸įæīĵ
    -0.06
    è§ģæĪij
    -0.06
    _SOFT
    -0.06
    lesen
    -0.06
    POSITIVE LOGITS
    abbo
    0.07
    è¿ĶåĽŀ顶éĥ¨
    0.07
    º¼
    0.07
    ï¼ļ
    0.07
    spre
    0.06
    Å¡ti
    0.06
    ÙħØ´
    0.06
    iach
    0.06
     Karr
    0.06
    ÑģÑĤвенно
    0.06
    Activations Density 0.118%

    No Known Activations