© 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. 16355
    Prev
    Next
    INDEX
    Explanations

    example / eg

    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
    çī¹æĸ¯
    -0.10
    åıĪä»İ
    -0.08
    ossa
    -0.07
    天å®ī
    -0.07
    æ±¹
    -0.07
    ÏĦÏģι
    -0.07
    .truth
    -0.07
    åĴĮ家åºŃ
    -0.07
    天水
    -0.07
    ipot
    -0.07
    POSITIVE LOGITS
     exemple
    0.07
    èĮĥ
    0.07
    示ä¾ĭ
    0.07
     example
    0.07
    /example
    0.07
    ä¾ĭåŃIJ
    0.06
     examples
    0.06
     renda
    0.06
    uf
    0.06
    -example
    0.06
    Activations Density 0.006%

    No Known Activations