© 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. 39755
    Prev
    Next
    INDEX
    Explanations

    keys with strings

    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
    士æŀĹ
    -0.07
    .exports
    -0.07
    lemi
    -0.07
    innacle
    -0.06
    mund
    -0.06
    mac
    -0.06
    Orm
    -0.06
    æĤ¨çļĦä½įç½®
    -0.06
    èĨ
    -0.06
    æĺĵåľ°
    -0.06
    POSITIVE LOGITS
    _some
    0.08
     mot
    0.08
     punishable
    0.08
    æŁIJæŁIJ
    0.07
     blah
    0.07
    æŁIJ
    0.07
    æµĭè¯ķ
    0.07
    _ENTRIES
    0.07
     foo
    0.07
    åĴĮæݧåĪ¶
    0.07
    Activations Density 0.735%

    No Known Activations