© 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. 24429
    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
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    称
    -0.08
    igh
    -0.08
    é¾Ļåįİ
    -0.08
     endlessly
    -0.07
    Reusable
    -0.07
    hower
    -0.07
    gesi
    -0.07
    åĿĩæĺ¯
    -0.07
    ãĥ«ãĤ¹
    -0.07
    POSITIVE LOGITS
     untouched
    0.10
     unchanged
    0.10
    ä¿ĿçķĻ
    0.10
    ä¿ĿçķĻäºĨ
    0.09
    ä¸įåĬ¨
    0.08
     vẹn
    0.08
     intact
    0.07
     until
    0.07
     preserving
    0.07
    ä¿ĿæĬ¤å¥½
    0.07
    Activations Density 0.036%

    No Known Activations