© 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. 22903
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    antic
    -0.09
    kan
    -0.08
     걸
    -0.07
    对ä¸Ĭè¿°
    -0.07
    оÑĢг
    -0.07
    ward
    -0.06
    urai
    -0.06
    ä»İ没
    -0.06
    odal
    -0.06
    crate
    -0.06
    POSITIVE LOGITS
    oples
    0.08
    ussy
    0.08
     Briggs
    0.07
    inky
    0.07
    åĪ¶åº¦çļĦ
    0.07
    å®ĪåĪĻ
    0.07
     Loader
    0.07
    orni
    0.07
    æŀ¶åŃIJ
    0.07
    اÙĨØ´
    0.07
    Activations Density 0.001%

    No Known Activations