© 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. 23604
    Prev
    Next
    INDEX
    Explanations

    correlated outcome variables

    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
    _INLINE
    -0.07
    度ãģ«
    -0.07
     upfront
    -0.07
    urf
    -0.06
    à¸ĵà¹Į
    -0.06
    usp
    -0.06
    å·²ç»ıæĬĬ
    -0.06
     triplet
    -0.06
    ีà¸Ķ
    -0.06
    itial
    -0.06
    POSITIVE LOGITS
     correlated
    0.09
     correl
    0.09
    æµĭéĩı
    0.09
     correlate
    0.08
    æ³¢åĬ¨
    0.08
    -mean
    0.08
     correlation
    0.08
    åģıå·®
    0.07
     Measurement
    0.07
    èµ·ä¼ı
    0.07
    Activations Density 0.010%

    No Known Activations