© 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. 48834
    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
     Bakal
    -0.08
    èį¡èį¡
    -0.07
    åħ¶éĹ´
    -0.07
    æĪij们身边
    -0.07
    ouser
    -0.07
    ä¸į移
    -0.07
    ä¼¼æĺ¯
    -0.07
    eroon
    -0.07
    ä¹ĭé«ĺ
    -0.07
    èĬĴ
    -0.07
    POSITIVE LOGITS
    ULA
    0.07
    INGS
    0.07
    ötz
    0.07
    iale
    0.07
    ulla
    0.07
    Ïĥμ
    0.07
     Äijầy
    0.07
    好好åŃ¦ä¹ł
    0.07
    ings
    0.06
    agram
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.