© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 19483
    Prev
    Next
    INDEX
    Explanations

    variable names or indices

    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
    orro
    -0.08
    .TypeOf
    -0.07
    éļĪ
    -0.07
    icans
    -0.06
    æīĢ欲
    -0.06
    åĽ½æĥħ
    -0.06
    èĨ½
    -0.06
    emann
    -0.06
    éļ»
    -0.06
    ydd
    -0.06
    POSITIVE LOGITS
    ä»¬ä¹Ł
    0.09
    çļĦé¦ĸ
    0.09
    们对
    0.08
    大伯
    0.08
    :first
    0.08
    νά
    0.08
    ä¹ĭä¸ĢçļĦ
    0.07
    人ä¸Ģ
    0.07
    apos
    0.07
    âĤģ
    0.07
    Activations Density 0.027%

    No Known Activations