© 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. 13309
    Prev
    Next
    INDEX
    Explanations

    multivariate statistical modeling

    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
    æıIJ
    -0.08
    æ®ĭéħ·
    -0.07
    æĨĶ
    -0.07
    otle
    -0.07
    eresa
    -0.07
    ظÙĬÙģ
    -0.07
    å¾ĢåIJİ
    -0.07
    éĺ¶
    -0.07
    åIJijèį£
    -0.07
    alu
    -0.07
    POSITIVE LOGITS
     joint
    0.10
    joint
    0.09
     correlation
    0.08
    åįı
    0.08
     prob
    0.08
    èģĶ
    0.08
    Joint
    0.08
     Joint
    0.08
     correlations
    0.08
    angk
    0.08
    Activations Density 0.006%

    No Known Activations