© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 54925
    Prev
    Next
    INDEX
    Explanations

    characteristics and qualities

    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
    Negative Logits
    ãģĵãģ¨ãģ«ãģªãĤĬãģ¾ãģĻ
    -0.07
    elsen
    -0.07
    ìłģìĿ´ê³ł
    -0.06
    æĽ´åħ¨
    -0.06
    estan
    -0.06
    irt
    -0.06
     döv
    -0.06
    ecil
    -0.06
    è®¾åľ¨
    -0.06
    gili
    -0.06
    POSITIVE LOGITS
    çŃīçī¹çĤ¹
    0.12
    qualities
    0.10
     qualities
    0.10
    åĮºåĪ«äºİ
    0.09
    对å¾ħ
    0.09
    oce
    0.09
    è¿ĻæŃ£æĺ¯
    0.08
    以èĩ³äºİ
    0.08
    èijĹ称
    0.08
     characteristics
    0.08
    Activations Density 0.355%

    No Known Activations