© 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. 55600
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    OrNil
    -0.07
    éĨ
    -0.07
    ernel
    -0.07
    ิà¸ĩ
    -0.07
    ="%
    -0.07
    è°ĵä¹ĭ
    -0.07
    çĿ¡çļĦ
    -0.06
     anon
    -0.06
    éĿĴæĿ¾
    -0.06
    Ñĥне
    -0.06
    POSITIVE LOGITS
    quo
    0.08
    achu
    0.08
    太è¿ĩäºİ
    0.08
    ajat
    0.07
    é¢ĺå¹²
    0.07
     distr
    0.07
     unrelated
    0.07
    irman
    0.07
     жи
    0.07
    ä¸į符åIJĪ
    0.07
    Activations Density 0.000%

    No Known Activations