© 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. 26710
    Prev
    Next
    INDEX
    Explanations

    percentage/chance of

    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
    apak
    -0.08
    èĮ¬
    -0.07
    ¹Ħ
    -0.07
    ibbon
    -0.07
     several
    -0.07
    á
    -0.07
    åd
    -0.06
    ë¥
    -0.06
    eg
    -0.06
    _BLK
    -0.06
    POSITIVE LOGITS
    å·¦åı³çļĦ
    0.10
    ä¹ĭå¤ļ
    0.08
    è¿Ļ个æķ°åŃĹ
    0.07
     Purt
    0.07
    uters
    0.07
    Æ°á»Łi
    0.07
    ä¹ĭæķ°
    0.07
    è¿Ļä¹Īå¤ļçļĦ
    0.07
    à¹īย
    0.07
    æľŁéĹ´å±¥è¡Į
    0.07
    Activations Density 0.084%

    No Known Activations