© 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. 23201
    Prev
    Next
    INDEX
    Explanations

    linked list node

    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
    对åİŁåijĬ
    -0.08
    ovsky
    -0.08
    .Strings
    -0.08
     opdr
    -0.08
    Enumerable
    -0.08
    çħŀ
    -0.07
    otic
    -0.07
    tings
    -0.07
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.07
    ä¹ĭæĢ¥
    -0.07
    POSITIVE LOGITS
    åĴĮä¿¡æģ¯
    0.07
    ั
    0.06
     Info
    0.06
    Info
    0.06
     tram
    0.06
    aix
    0.06
    èĩªä¹ł
    0.06
    åŁºæľ¬ä¿¡æģ¯
    0.06
    .Pointer
    0.06
    ä¸īåħĥ
    0.06
    Activations Density 0.108%

    No Known Activations