© 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. 33974
    Prev
    Next
    INDEX
    Explanations

    Difference between concepts

    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
    лак
    -0.09
    luck
    -0.08
    ér
    -0.08
    ernaut
    -0.08
     @_
    -0.08
    类似éĹ®é¢ĺ
    -0.08
    æİ¥çıŃ
    -0.08
    åıĪéģĵ
    -0.08
    åı¯æĥ³èĢĮçŁ¥
    -0.07
    ieg
    -0.07
    POSITIVE LOGITS
    Âł
    0.07
    ยำ
    0.06
     —
    0.06
    ıra
    0.06
    æĪIJå¥Ĺ
    0.06
    éļ
    0.05
    çŃĶæ¡Īæĺ¯
    0.05
    âĢ
    0.05
     unequiv
    0.05
    èĢĺ
    0.05
    Activations Density 0.064%

    No Known Activations