© 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. 43969
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with derivatives

    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
    æĺĵçĪĨ
    -0.07
    ete
    -0.06
    éģįåıĬ
    -0.06
    -align
    -0.06
     enough
    -0.06
    å¤ıãģ®
    -0.06
    -opacity
    -0.06
    头ä¸ĬçļĦ
    -0.06
    nil
    -0.06
    eto
    -0.06
    POSITIVE LOGITS
    ché
    0.08
    åľ¨ä¸ĢæĹģ
    0.07
    pping
    0.07
    unesse
    0.07
    esper
    0.07
    伶
    0.07
    èĺ
    0.07
    mund
    0.06
    pper
    0.06
    éĺ
    0.06
    Activations Density 0.005%

    No Known Activations