© 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. 23350
    Prev
    Next
    INDEX
    Explanations

    URL path separators or fractions

    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
     somehow
    -0.08
     sometime
    -0.07
     poš
    -0.07
    sdale
    -0.07
    åħ¢
    -0.07
    çĶ±åİŁåijĬ
    -0.07
    ussion
    -0.07
    置身äºİ
    -0.07
    fw
    -0.07
    对äºİæĪij们
    -0.06
    POSITIVE LOGITS
    ROUND
    0.06
    åĮºéķ¿
    0.06
    ↵
    0.06
    arel
    0.06
    åıĪ以
    0.06
     autoria
    0.06
    èµŀæĪIJ
    0.06
    ariado
    0.06
    ãģĭãĤĵ
    0.06
    æ¿
    0.06
    Activations Density 0.025%

    No Known Activations