© 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. 43946
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols after words

    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
    rana
    -0.07
    aset
    -0.07
    ulam
    -0.07
    isasi
    -0.07
    éĿ¢å¯¹
    -0.07
    è¶ħ级
    -0.07
     воз
    -0.07
    APER
    -0.07
    :>
    -0.07
    濯
    -0.07
    POSITIVE LOGITS
    ä¹ĭæĢ¥
    0.07
    auté
    0.07
    ç»ı常æĢ§
    0.07
    ÙĮÙij
    0.07
    puted
    0.07
    éķ¿éĿĴ
    0.07
    adier
    0.06
    enheim
    0.06
    iggio
    0.06
    mons
    0.06
    Activations Density 0.001%

    No Known Activations