© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22763
    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
    aily
    -0.08
    ÑĢгÑĥ
    -0.08
    nyt
    -0.08
    ìľ¨
    -0.08
    utzt
    -0.07
    icom
    -0.07
    imei
    -0.07
    æľ¬äººåľ¨
    -0.07
    ional
    -0.07
    toggleClass
    -0.07
    POSITIVE LOGITS
    orit
    0.08
    æŃ£å¤§
    0.07
    æĪĸèĢħæĺ¯
    0.07
    ä¿ĬæĿ°
    0.07
    åı¯èĥ½æĺ¯åĽłä¸º
    0.06
    çѱ
    0.06
    ou
    0.06
    大åĸľ
    0.06
    eon
    0.06
     quite
    0.06
    Activations Density 0.000%

    No Known Activations