© 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. 18508
    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
    åĬ¡
    -0.07
     sav
    -0.07
     Mur
    -0.07
    OwnerId
    -0.06
    æĸ½å·¥è¿ĩç¨ĭä¸Ń
    -0.06
    uild
    -0.06
    æī¿æı½
    -0.06
    اÙģت
    -0.06
    ouch
    -0.06
    =nil
    -0.06
    POSITIVE LOGITS
    yer
    0.08
    hors
    0.08
    yo
    0.07
    essler
    0.07
    иÑģÑĤÑĢа
    0.07
    çļĦæľīåĬĽ
    0.07
    _terms
    0.07
    FINAL
    0.07
    à¸ī
    0.07
    olle
    0.07
    Activations Density 0.000%

    No Known Activations