© 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. 14832
    Prev
    Next
    INDEX
    Explanations

    derivative of variables

    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
    两åѦä¸Ģåģļ
    -0.08
     pakar
    -0.07
    åı°ä¸ĬçļĦ
    -0.07
    pekt
    -0.07
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    å¤ļèĤī
    -0.07
     remarqu
    -0.07
    ToDate
    -0.07
    PARATOR
    -0.07
    >".
    -0.07
    POSITIVE LOGITS
    èĬ·
    0.07
    eldes
    0.06
    zzle
    0.06
    wards
    0.06
     gesta
    0.06
    istol
    0.06
     direction
    0.06
    åħ¼
    0.06
     TES
    0.06
     sense
    0.06
    Activations Density 0.003%

    No Known Activations