© 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. 40764
    Prev
    Next
    INDEX
    Explanations

    Lesser General Public License

    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
    å½Ĵ
    -0.07
    kv
    -0.07
    ikä
    -0.06
    ilu
    -0.06
    кова
    -0.06
    大æĶ¾
    -0.06
    wati
    -0.06
    天æĺİ
    -0.06
    äºĨåij¢
    -0.06
    ä¸ĢèĤ¡
    -0.06
    POSITIVE LOGITS
    使çĶ¨æĿĥ
    0.08
    emt
    0.07
    wizard
    0.07
    æĪĸ缴æİ¥
    0.07
    .son
    0.07
    æĿĪ
    0.07
    ç»ıèIJ¥çĬ¶åĨµ
    0.07
    emen
    0.07
    erville
    0.07
    inaire
    0.07
    Activations Density 0.022%

    No Known Activations