© 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. 48614
    Prev
    Next
    INDEX
    Explanations

    initials and names

    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
    åħ¶å®ĥåªĴä½ĵ
    -0.07
    æĢ§ä»¥åıĬ
    -0.07
    å¿ĥçĹħ
    -0.07
    å¿Į
    -0.07
    æĦŁåĴĮ
    -0.07
    lock
    -0.07
    ä¸įåİĮ
    -0.07
    éģı
    -0.06
    ä¸į强
    -0.06
    леÑĤиÑı
    -0.06
    POSITIVE LOGITS
    éģ¸éłħ
    0.10
    éĢī项
    0.10
     option
    0.09
    çŃĶæ¡Ī解æŀIJ
    0.08
    åįķéĢīé¢ĺ
    0.08
    oran
    0.08
     گزÛĮÙĨÙĩ
    0.07
     Option
    0.07
    ìĤŃ
    0.07
    岸
    0.07
    Activations Density 0.011%

    No Known Activations