© 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. 65485
    Prev
    Next
    INDEX
    Explanations

    commas and clauses

    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
    vlak
    -0.08
     Attra
    -0.07
    #
    -0.07
    inters
    -0.07
    enca
    -0.07
    erien
    -0.07
    ãģ¾ãģ§ãģ«
    -0.07
    ammers
    -0.07
    ezu
    -0.07
    �t
    -0.07
    POSITIVE LOGITS
    èĢĥèĻijåĪ°
    0.08
    ä¹Łæĺ¯æľĢ
    0.07
    áĥĹ
    0.07
    Ùħا
    0.07
    ik
    0.07
    è¦ģæĺİç¡®
    0.07
    å¦Ĥæŀľåıªæĺ¯
    0.06
    ç»ıæŁ¥
    0.06
    ],&
    0.06
    ä
    0.06
    Activations Density 0.002%

    No Known Activations