© 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. 3910
    Prev
    Next
    INDEX
    Explanations

    numbering sequences

    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
    ınd
    -0.08
    æľĢæĸ°è¯Ħ论
    -0.07
    ŀ
    -0.07
    /conf
    -0.07
     ‘
    -0.07
    æķħåIJį
    -0.07
    lein
    -0.07
    culus
    -0.07
    æĥŁæľī
    -0.07
    —for
    -0.06
    POSITIVE LOGITS
    以åıĬ
    0.08
    wnd
    0.07
    度çļĦ
    0.07
    ilib
    0.06
    lipp
    0.06
    ï¸ı
    0.06
    czyn
    0.06
    度
    0.06
    éľĦ
    0.06
    祺
    0.06
    Activations Density 0.087%

    No Known Activations