© 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. 57712
    Prev
    Next
    INDEX
    Explanations

    Now, then sequences

    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
    arius
    -0.08
    {}_
    -0.07
    braco
    -0.07
    ourcem
    -0.07
    ä¸Ģ缴ä¿ĿæĮģ
    -0.06
    ovol
    -0.06
    ä¸Ģ身
    -0.06
    继ç»Ń沿
    -0.06
    çļİ
    -0.06
    odox
    -0.06
    POSITIVE LOGITS
     Saar
    0.08
    gle
    0.07
    æŃ£å¼ıçļĦ
    0.07
    çĭłçĭłçļĦ
    0.07
     puntu
    0.07
    elves
    0.06
    åľ¨æľĢåIJİ
    0.06
    اÙĨات
    0.06
    ady
    0.06
    asco
    0.06
    Activations Density 0.002%

    No Known Activations