© 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. 33448
    Prev
    Next
    INDEX
    Explanations

    places and items

    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
    eldon
    -0.07
    à¹Ģศษ
    -0.07
    ually
    -0.07
    èģĮåĬ¡
    -0.07
    è³ĩ
    -0.07
    åħ§çļĦ
    -0.07
    ness
    -0.06
    -mediated
    -0.06
     xá»ī
    -0.06
    æŶéĹ´åĨħ
    -0.06
    POSITIVE LOGITS
    گاÙĩ
    0.10
     setC
    0.09
     ëĭ¨ì§Ģ
    0.09
    æłĪ
    0.08
    блок
    0.08
    atorium
    0.08
    æŀ
    0.08
    terek
    0.08
    bila
    0.08
    plex
    0.07
    Activations Density 0.865%

    No Known Activations