© 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. 33353
    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
    ائÙģ
    -0.07
    ÙĪÙģ
    -0.07
    åįĵ
    -0.06
    å¸Ń
    -0.06
    anco
    -0.06
    æĭ¾
    -0.06
    åĹ£
    -0.06
    }'",
    -0.06
    imore
    -0.06
    Bootstrap
    -0.06
    POSITIVE LOGITS
    orthy
    0.08
    ãĤ½ãĥ¼
    0.07
    hurst
    0.07
    aska
    0.07
    ÄĽl
    0.07
    pras
    0.07
    çķı
    0.07
    ç»ĻæĪijçķĻè¨Ģ
    0.07
    ä¸Ģåľ°
    0.06
     Salone
    0.06
    Activations Density 0.000%

    No Known Activations