© 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. 32161
    Prev
    Next
    INDEX
    Explanations

    depression in boys""in that order""England Vs India""o or v""in the stent group""compare this time""take precedence""fades a picture out""or z""service1 version taking"

    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
    ias
    -0.08
    AGR
    -0.07
    æ³ķåĴĮ
    -0.06
    羣åģĩ
    -0.06
    ult
    -0.06
    udy
    -0.06
    æŁ³
    -0.06
    æ³ķ
    -0.06
     tor
    -0.06
    ator
    -0.06
    POSITIVE LOGITS
    ãģ»ãģĨãģĮ
    0.09
    æĽ´ç²¾å½©
    0.08
    olulu
    0.08
    ãģ®æĸ¹ãģĮ
    0.08
    ulet
    0.08
    æĽ´æĺĵ
    0.08
    æĽ´ç¾İ好
    0.08
    æĽ´å¤ļåĽŀçŃĶ
    0.08
    коно
    0.07
    æĽ´åºĶ该
    0.07
    Activations Density 0.012%

    No Known Activations