© 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. 25568
    Prev
    Next
    INDEX
    Explanations

    stationary phase, cerebral artery

    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
    个头
    -0.07
    æľ±åħĥ
    -0.07
    ander
    -0.07
    人äºĨ
    -0.06
    odies
    -0.06
    agl
    -0.06
    enson
    -0.06
    å§ĭèĩ³
    -0.06
    aglia
    -0.06
    iones
    -0.06
    POSITIVE LOGITS
    æĿijæĿijæ°ij
    0.10
    ä¸ŃçļĦæķ°æį®
    0.10
    éĿ¢ä¸ĬçļĦ
    0.09
    ä¸ŃçļĦéĩįè¦ģ
    0.09
    å±ĤçļĦ
    0.09
    -phase
    0.09
    åĮºçļĦ
    0.09
    é¢ĨåŁŁçļĦ
    0.09
    æľŁéĹ´çļĦ
    0.09
    éĺ¶æ®µçļĦ
    0.09
    Activations Density 0.661%

    No Known Activations