© 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. 55382
    Prev
    Next
    INDEX
    Explanations

    percentages and quantities

    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
    waran
    -0.09
    iette
    -0.08
     Viernes
    -0.08
    usher
    -0.08
     retribu
    -0.08
    hin
    -0.07
    ivia
    -0.07
    hta
    -0.07
    ÅĤad
    -0.07
    _FATAL
    -0.07
    POSITIVE LOGITS
    æĺ¯ä»Ģä¹ĪæĦıæĢĿ
    0.06
    rouw
    0.06
    ä»Ģä¹ĪæĦıæĢĿ
    0.06
    çĭĤ
    0.06
    à¹ĩ
    0.06
    äºİ
    0.06
    ForObject
    0.06
    æ´
    0.06
    Âł
    0.06
    æı
    0.06
    Activations Density 0.004%

    No Known Activations