© 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. 4114
    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
    æĶ¶èĹıæľ¬ç«Ļ
    -0.07
    artial
    -0.07
    ulas
    -0.07
    æŦ
    -0.07
    voud
    -0.07
    aisin
    -0.07
    <IEnumerable
    -0.07
    etos
    -0.07
    eti
    -0.07
    ziale
    -0.07
    POSITIVE LOGITS
    ↵
    0.08
    hm
    0.07
    rauch
    0.07
    kea
    0.07
    omme
    0.06
     Betroffenen
    0.06
    ä½łèĩªå·±çļĦ
    0.06
    HM
    0.06
    æĹłåĩł
    0.06
    rag
    0.06
    Activations Density 0.000%

    No Known Activations