© 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. 12669
    Prev
    Next
    INDEX
    Explanations

    lists of items or arithmetic

    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
    ç¿»äºĨ
    -0.07
    wart
    -0.07
    erti
    -0.07
    arin
    -0.07
    elin
    -0.07
     tém
    -0.07
    æ·ĺ
    -0.07
    olid
    -0.07
    ChangeListener
    -0.07
    ovin
    -0.06
    POSITIVE LOGITS
    lector
    0.07
    eva
    0.07
     ÙħÙĪضع
    0.06
    lando
    0.06
    è¿Ļ个éĹ®é¢ĺçļĦ
    0.06
    éļı
    0.06
    æ³Ĭ
    0.06
    (*)
    0.06
    ebbe
    0.06
    "x
    0.06
    Activations Density 0.001%

    No Known Activations