© 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. 43642
    Prev
    Next
    INDEX
    Explanations

    trade, balances, or rates

    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
    haal
    -0.07
    ortable
    -0.07
    èĭ¦å¿ĥ
    -0.07
    Ø´ÙĨ
    -0.07
     '..',
    -0.07
    åĹĵ
    -0.07
    voire
    -0.07
    ç§ĴæĿĢ
    -0.07
    æ°´çħ®
    -0.06
    енÑĤа
    -0.06
    POSITIVE LOGITS
    trade
    0.07
     mole
    0.07
    _transition
    0.07
    (rate
    0.07
    balances
    0.07
    aines
    0.07
    红æ¢ħ
    0.07
     trade
    0.06
    ä¸ĩéĩĮ
    0.06
     Desired
    0.06
    Activations Density 0.001%

    No Known Activations