© 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. 62274
    Prev
    Next
    INDEX
    Explanations

    correlation and function

    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
    evas
    -0.07
    ActionResult
    -0.07
    大åı£
    -0.07
     decid
    -0.07
    athed
    -0.07
    andie
    -0.07
    ÑĥÑĢг
    -0.07
    ildir
    -0.07
    å¤ļéĢī
    -0.07
     suor
    -0.07
    POSITIVE LOGITS
    è¡°
    0.09
     lag
    0.08
    ť
    0.08
    è¡°åĩı
    0.08
    lag
    0.08
    缸éļĶ
    0.08
     correlation
    0.08
    è¿ľè·Ŀ离
    0.07
     decay
    0.07
     Fourier
    0.07
    Activations Density 0.006%

    No Known Activations