© 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. 56999
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    åĬ¡
    -0.09
    idet
    -0.08
     Gres
    -0.07
    åĭĻ
    -0.07
    顾åIJįæĢĿä¹ī
    -0.07
    峪
    -0.07
    åħĭéļ¾
    -0.07
    Nap
    -0.07
    æī«é»ij
    -0.07
    Href
    -0.07
    POSITIVE LOGITS
    åıĮèĬĤ
    0.06
    onga
    0.06
    æĺ¯æľĢ大çļĦ
    0.06
    taglia
    0.06
    roud
    0.06
    ril
    0.06
    ubit
    0.06
    enom
    0.06
     Dung
    0.06
    海伦
    0.06
    Activations Density 0.121%

    No Known Activations