© 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. 27088
    Prev
    Next
    INDEX
    Explanations

    miles on Wednesday, five miles on Friday, and six miles on Sunday

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    æĭ¬
    -0.07
    对åĨħ
    -0.07
    वल
    -0.06
    æī¿æĭħèµĶåģ¿è´£ä»»
    -0.06
    Beh
    -0.06
    èģļ
    -0.06
    ä¸įé½IJ
    -0.06
    åĴĮåįķä½į
    -0.06
    飬
    -0.06
    ধ
    -0.06
    POSITIVE LOGITS
     sekal
    0.08
    第äºĮ大
    0.07
     reduc
    0.07
    éĻ£
    0.07
    èĤ¥
    0.07
    algo
    0.07
    æ¾Ī
    0.07
    åı¯æľĽ
    0.07
    çĶ¸
    0.07
    èĬĬ
    0.07
    Activations Density 0.002%

    No Known Activations