© 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. 50745
    Prev
    Next
    INDEX
    Explanations

    presence or use

    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
    ä¹ĭä¸ĢçļĦ
    -0.07
    _THAT
    -0.06
     wonders
    -0.06
    å½ĵä»ĸ
    -0.06
    åħ¼
    -0.06
    UNE
    -0.06
    ochen
    -0.06
    渣
    -0.06
    åħ¨ä½ĵ
    -0.06
    éĤ£å°±æĺ¯
    -0.06
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.14
    æľ¬èº«
    0.10
    æľ¬èº«å°±
    0.10
    è¿Ļæł·ä¸Ģ个
    0.09
     presence
    0.09
     itself
    0.09
    usch
    0.09
    presence
    0.08
    ä¼ļå¼ķèµ·
    0.08
     ìŀIJì²´ê°Ģ
    0.08
    Activations Density 0.308%

    No Known Activations