© 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. 33363
    Prev
    Next
    INDEX
    Explanations

    in a nutshell or summary

    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
     filiale
    -0.08
    LIKELY
    -0.08
    éĶ¦æ¶Ľ
    -0.08
    antica
    -0.08
    klik
    -0.07
    chnik
    -0.07
    ạ
    -0.07
     Schau
    -0.07
    embro
    -0.07
    ç«ŁçĦ¶
    -0.07
    POSITIVE LOGITS
    综ä¸Ĭ
    0.13
     summary
    0.11
    æĢ»ç»ĵ
    0.11
     summar
    0.10
    æĢ»èĢĮè¨Ģä¹ĭ
    0.10
    综ä¸ĬæīĢè¿°
    0.09
    Summary
    0.09
     summarize
    0.09
    summary
    0.09
     summarized
    0.09
    Activations Density 0.010%

    No Known Activations