© 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. 57205
    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
    jeÄį
    -0.07
    thon
    -0.07
    éco
    -0.07
    alo
    -0.06
    setData
    -0.06
    åĴĮåĬªåĬĽ
    -0.06
    çļĦæķ°æį®æĺ¾ç¤º
    -0.06
    åĽ½å®¶ç¨İåĬ¡æĢ»å±Ģ
    -0.06
    Ñĥй
    -0.06
    ÑĤÑĢÑĥ
    -0.06
    POSITIVE LOGITS
    IZE
    0.08
    ize
    0.08
    aldi
    0.08
    è½¼
    0.07
    åŁĶ
    0.07
    zug
    0.07
    æݪ
    0.07
     ר×ķ
    0.07
     tod
    0.06
    .ms
    0.06
    Activations Density 0.000%

    No Known Activations