© 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. 49714
    Prev
    Next
    INDEX
    Explanations

    code headers

    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
     ÑģамомÑĥ
    -0.07
     JSX
    -0.07
    ÑĢÑĤи
    -0.06
    åĮ»èį¯åį«çĶŁ
    -0.06
    å°±åı¯
    -0.06
    ಣ
    -0.06
    çĥŃéŨæݨèįIJ
    -0.06
     insomma
    -0.06
    iny
    -0.06
    standing
    -0.06
    POSITIVE LOGITS
    ä¸İéĿŀ
    0.08
    éĹ»
    0.08
     additionally
    0.07
    æľī家
    0.07
    åĴĮéĿŀ
    0.07
    aign
    0.07
    #error
    0.07
    [`
    0.07
    ByUsername
    0.07
    resi
    0.07
    Activations Density 0.048%

    No Known Activations