© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63030
    Prev
    Next
    INDEX
    Explanations

    relative stability, efficacy, multiples, ratio

    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
    æĹ
    -0.07
    lis
    -0.07
    çĽ¸ä¿¡æĪij
    -0.07
    å¤§ä¾ł
    -0.07
    coni
    -0.07
    .OR
    -0.07
    scription
    -0.07
    scriptions
    -0.07
    ä¸īæ¸ħ
    -0.06
    cions
    -0.06
    POSITIVE LOGITS
    åįİå¾·
    0.08
     ratio
    0.07
    éĻª
    0.07
    åij¼
    0.07
     Rat
    0.07
    éĻªä¼´
    0.07
    åIJŁ
    0.07
     ratios
    0.07
    åĨ
    0.07
     Ratio
    0.07
    Activations Density 0.057%

    No Known Activations