© 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. 16472
    Prev
    Next
    INDEX
    Explanations

    numbers followed by operations

    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
     Blasio
    -0.10
    ymar
    -0.09
     Sán
    -0.09
    getManager
    -0.08
    iface
    -0.08
    fris
    -0.08
    åľ¨æīĢ
    -0.08
    #w
    -0.08
    ÙĩÙı
    -0.08
    å·¥åѦéĻ¢
    -0.08
    POSITIVE LOGITS
    stin
    0.07
    ÏĦζ
    0.06
    ilde
    0.06
    ce
    0.06
    cec
    0.05
    ife
    0.05
    æķ´åIJĪ
    0.05
    ç¼Ģ
    0.05
    èĢĮæĪIJ
    0.05
    éĥ¨
    0.05
    Activations Density 0.174%

    No Known Activations