© 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. 3410
    Prev
    Next
    INDEX
    Explanations

    January

    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
    ä¹ĿæľĪ
    -0.07
    çĥĪæĹ¥
    -0.07
    eward
    -0.06
    çī©çļĦ
    -0.06
    èį«
    -0.06
    åħŃæľĪ
    -0.06
    ence
    -0.06
    æļ´æĻĴ
    -0.06
    TEM
    -0.06
    ادÙĬÙĨ
    -0.06
    POSITIVE LOGITS
    å¤§éĽª
    0.11
    å°ıéĽª
    0.10
     ÙĥاÙĨÙĪÙĨ
    0.09
    çļĦéĽª
    0.08
    ç§¯éĽª
    0.08
    lemetry
    0.08
    HING
    0.08
    å¯Ĵæ½®
    0.08
    _DESCRIPTOR
    0.08
    à§įথ
    0.08
    Activations Density 0.309%

    No Known Activations