© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13690
    Prev
    Next
    INDEX
    Explanations

    for example

    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´»
    -0.07
    NEXT
    -0.07
    asse
    -0.06
    éĴĵ
    -0.06
     momentarily
    -0.06
    wai
    -0.06
    çĦī
    -0.06
     Debate
    -0.06
    osso
    -0.06
    loo
    -0.06
    POSITIVE LOGITS
     examples
    0.10
     Examples
    0.10
     example
    0.10
    示ä¾ĭ
    0.10
    examples
    0.09
    Examples
    0.09
    example
    0.09
     Example
    0.09
     exemple
    0.09
    ä¾ĭåŃIJ
    0.08
    Activations Density 0.012%

    No Known Activations