© 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. 37568
    Prev
    Next
    INDEX
    Explanations

    measurement or abstract quality suffix

    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
     ób
    -0.07
    essant
    -0.07
    logan
    -0.07
    edel
    -0.07
     GÅĤów
    -0.07
    oug
    -0.07
    estet
    -0.07
    overrides
    -0.07
     McCorm
    -0.07
    _literals
    -0.07
    POSITIVE LOGITS
    è¡¡éĩı
    0.10
     measure
    0.10
    çļĦæ¦Ĥ念
    0.09
    è¶Ĭ大
    0.09
     measures
    0.08
    å®ļä¹ī为
    0.08
    æĮĩçļĦæĺ¯
    0.08
    度éĩı
    0.08
    è¶Ĭä½İ
    0.08
    Measure
    0.08
    Activations Density 0.021%

    No Known Activations