© 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. 30417
    Prev
    Next
    INDEX
    Explanations

    peace and quiet

    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
    æĬĺ
    -0.08
    سخ
    -0.07
    ä¸įæŃ¢
    -0.07
    ä¸įåıª
    -0.07
    温æļĸ
    -0.07
    åıªä¸įè¿ĩ
    -0.07
    éļı
    -0.07
    angkit
    -0.07
    ?=.*
    -0.07
     inse
    -0.06
    POSITIVE LOGITS
     isolation
    0.15
     isol
    0.14
    å¹²åĩĢ
    0.14
    纯åĩĢ
    0.14
     isolate
    0.13
     clean
    0.13
    æ´ģåĩĢ
    0.13
    éļĶç»Ŀ
    0.13
    å¹²åĩĢçļĦ
    0.13
    æ¸ħåĩĢ
    0.12
    Activations Density 0.326%

    No Known Activations