© 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. 14230
    Prev
    Next
    INDEX
    Explanations

    this followed by a noun

    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
    æĮĩå®ļ
    -0.07
    Âł
    -0.07
    è¯ģæį®è¯ģæĺİ
    -0.06
    aint
    -0.06
     airstrikes
    -0.06
    横
    -0.06
    该项
    -0.06
    à¹Ģà¸Ľà¹ĩà¸Ļà¸ķัว
    -0.06
    iesel
    -0.06
    å¤§åľ°
    -0.06
    POSITIVE LOGITS
    çļĦäºĭä¸ļ
    0.09
    SSION
    0.09
    è¿Ļä¸ĢåĪĩ
    0.08
    zzo
    0.08
    ä¸Ģå¼łå¼ł
    0.07
    ä¸Ĭä¸Ģç«ł
    0.07
    ÃŃdia
    0.07
    FileSize
    0.07
    abis
    0.07
    å°±æĺ¯è¿Ļæł·
    0.07
    Activations Density 0.144%

    No Known Activations