© 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. 23844
    Prev
    Next
    INDEX
    Explanations

    purification protocols and methods

    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
     Wiring
    -0.08
     drew
    -0.08
    éĻª
    -0.07
     kalkul
    -0.07
     calcul
    -0.07
    秸
    -0.07
     нака
    -0.07
    ç¯Ĩ
    -0.07
    éĢŀ
    -0.07
    ç¯Ģ
    -0.06
    POSITIVE LOGITS
     separation
    0.11
    æ´Ĺ涤
    0.09
     filtration
    0.09
    è¿Ļç§įæĸ¹æ³ķ
    0.09
     sépar
    0.09
     separating
    0.09
    æĵįä½ľæŃ¥éª¤
    0.09
    åĪĨ离
    0.09
     followed
    0.09
    åİ»éĻ¤
    0.09
    Activations Density 0.050%

    No Known Activations