© 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. 32482
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    æľ¬ç½ijç«Ļ
    -0.08
    çĴŁ
    -0.07
    anie
    -0.07
    maj
    -0.07
    çijķ
    -0.07
    à°²à±ĩ
    -0.07
     arrog
    -0.07
    omid
    -0.07
    ØŃب
    -0.07
    æľ¬ç«ĻæīĢæľī
    -0.07
    POSITIVE LOGITS
    cad
    0.08
    anten
    0.07
    ogo
    0.07
    çŃĶ
    0.07
    åŃIJäºĨ
    0.07
    æĸĩæľ«
    0.06
     stares
    0.06
    ogg
    0.06
    utton
    0.06
    æ´»äºĨ
    0.06
    Activations Density 0.001%

    No Known Activations