© 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. 61736
    Prev
    Next
    INDEX
    Explanations

    type I, AK, factor V, MN

    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
    æ°´åĻ¨
    -0.08
    çĶ±é«ĺ
    -0.07
    CRY
    -0.07
     AAA
    -0.06
    xfd
    -0.06
    أس
    -0.06
    åħ³æ³¨åħ¬ä¼Ĺåı·
    -0.06
    aing
    -0.06
    -tool
    -0.06
    Facade
    -0.06
    POSITIVE LOGITS
    ubb
    0.08
    ergestellt
    0.07
    å¼ı
    0.07
    ä¸ĭåIJĮ
    0.07
    æĭīåħĭ
    0.07
    sic
    0.07
    å¥ı
    0.07
    ientos
    0.07
    illac
    0.06
    殿ä¸ĭ
    0.06
    Activations Density 0.182%

    No Known Activations