© 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. 31258
    Prev
    Next
    INDEX
    Explanations

    imbalanced distribution or proportions

    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
    ndef
    -0.08
    æľĢéķ¿
    -0.08
    _maximum
    -0.08
    fam
    -0.07
    [length
    -0.07
     dissip
    -0.07
    resso
    -0.07
    é»Ħç´ł
    -0.07
    WithPath
    -0.07
    ocus
    -0.07
    POSITIVE LOGITS
     proportions
    0.18
    æ¯Ķä¾ĭ
    0.15
    æ¯Ķä¾ĭçļĦ
    0.15
     proportion
    0.14
     ratios
    0.14
     percentages
    0.14
    æ¯Ķä¾ĭ为
    0.14
    åĪĨå¸ĥ
    0.13
     distribution
    0.13
    çļĦæ¯Ķä¾ĭ
    0.13
    Activations Density 0.091%

    No Known Activations