© 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. 48358
    Prev
    Next
    INDEX
    Explanations

    perturbation, deviation, error

    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
     Bench
    -0.07
    /*@
    -0.06
     Aper
    -0.06
    ãĤµãĤ¤
    -0.06
     bench
    -0.06
    é£İæĻ¯åIJįèĥľ
    -0.06
    é¦ĸå¯Į
    -0.06
    epak
    -0.06
    çļĦ缸åħ³åĨħ容
    -0.06
     rich
    -0.06
    POSITIVE LOGITS
    /error
    0.10
    误差
    0.08
    çķĮéĻIJ
    0.08
    çķĮ
    0.08
    æ®ĭ
    0.08
     ÄijÃłn
    0.08
    åĶı
    0.07
    error
    0.07
    ×IJ×ķת
    0.07
     deviation
    0.07
    Activations Density 0.003%

    No Known Activations