© 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. 4025
    Prev
    Next
    INDEX
    Explanations

    hybrid features filters tests

    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
    Unified
    -0.08
    Äĵt
    -0.07
    让çĶŁæ´»
    -0.07
    绣ä¸ĢçļĦ
    -0.07
    éļıå¤Ħ
    -0.07
    åIJijèį£
    -0.07
    æľĢåīį沿
    -0.07
     parado
    -0.07
     foresee
    -0.07
    åĪĩå°Ķ
    -0.07
    POSITIVE LOGITS
    æĪİ
    0.08
     orthogonal
    0.07
     evaluations
    0.07
     kac
    0.07
    第äºĮ人æ°ijåĮ»éĻ¢
    0.07
    eluk
    0.07
    chnitt
    0.07
     monop
    0.07
    à¸Ħวามà¹Ģà¸Ľà¹ĩà¸Ļ
    0.07
     evaluation
    0.06
    Activations Density 0.008%

    No Known Activations