© 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. 51569
    Prev
    Next
    INDEX
    Explanations

    weighted sums and ratios

    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
     ÑģÑĥп
    -0.07
     deduction
    -0.07
    ãģļãĤĮ
    -0.07
    طة
    -0.07
    rott
    -0.07
    æİł
    -0.07
    ulg
    -0.07
     Authorization
    -0.07
    æķ¢
    -0.07
     Kub
    -0.07
    POSITIVE LOGITS
     ratios
    0.09
     Rat
    0.08
     weights
    0.08
     weighting
    0.08
     sums
    0.07
     contributions
    0.07
     proportional
    0.07
    æ´»åĬĽ
    0.07
     competing
    0.07
    _weights
    0.07
    Activations Density 0.009%

    No Known Activations