© 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. 39767
    Prev
    Next
    INDEX
    Explanations

    talking to you

    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
    æķħåIJį
    -0.07
    å¦Ĥ
    -0.07
    éģ¥éģ¥
    -0.06
    æ³ĽæĮĩ
    -0.06
    让广大
    -0.06
    erre
    -0.06
    .writ
    -0.06
    borough
    -0.06
    arian
    -0.06
    eced
    -0.06
    POSITIVE LOGITS
    æİ¥ä¸ĭæĿ¥çļĦ
    0.07
    ضÙħ
    0.07
    ضØŃ
    0.07
    éĩĪ
    0.07
    _INCLUDED
    0.07
    engin
    0.07
    éĢĤå½ĵ
    0.07
     caut
    0.07
    æ°Ĺ
    0.07
    δο
    0.07
    Activations Density 0.006%

    No Known Activations