© 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. 4197
    Prev
    Next
    INDEX
    Explanations

    future directions and perspectives

    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
    åħ¨ç¨ĭ
    -0.07
    ÑĩаÑı
    -0.07
    éĹ´æİ¥
    -0.07
    è¡Į使
    -0.06
    æ¶ĪèĢĹ
    -0.06
    å¿ĥçIJĨ
    -0.06
    åıįå¤į
    -0.06
    orial
    -0.06
    ä»ĵ
    -0.06
    缸å½ĵäºİ
    -0.06
    POSITIVE LOGITS
     future
    0.16
    æľªæĿ¥çļĦ
    0.14
    future
    0.14
    å±ķæľĽ
    0.14
    çļĦæľªæĿ¥
    0.14
    æľªæĿ¥åıijå±ķ
    0.13
    åıijå±ķæĸ¹åIJij
    0.13
     Future
    0.13
    Future
    0.13
    å±ķæľĽæľªæĿ¥
    0.13
    Activations Density 0.267%

    No Known Activations