© 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. 21211
    Prev
    Next
    INDEX
    Explanations

    only to / without / not / wants

    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
    erland
    -0.08
    elang
    -0.08
    ä¹Łæĺ¯æĪij
    -0.08
    ä¹Łæĺ¯ä¸Ģæł·
    -0.08
    crap
    -0.08
    typeName
    -0.08
    æĤ¨çļĦä½įç½®
    -0.08
    alette
    -0.08
    rapper
    -0.08
    ombat
    -0.08
    POSITIVE LOGITS
    Âł
    0.07
    unc
    0.06
     meaning
    0.06
     der
    0.05
     meaningful
    0.05
    ing
    0.05
    еÑĩ
    0.05
    اÙĨØ´
    0.05
    't
    0.05
     Clause
    0.05
    Activations Density 0.073%

    No Known Activations