© 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. 42379
    Prev
    Next
    INDEX
    Explanations

    previous

    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
    举èĩ³
    -0.07
    elaar
    -0.06
    amenti
    -0.06
    es
    -0.06
    ä¸Ģ个
    -0.06
    饶
    -0.06
    大å®Ŀ
    -0.06
    央
    -0.06
     templ
    -0.06
     discret
    -0.06
    POSITIVE LOGITS
     terakhir
    0.09
     пÑĢедÑĭ
    0.09
     précédente
    0.09
     previous
    0.09
    ä¸Ĭä¸Ģ
    0.09
    tsy
    0.08
    æľĢåIJİä¸Ģ
    0.08
    stro
    0.08
     vorige
    0.08
     precedenti
    0.08
    Activations Density 0.021%

    No Known Activations