© 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. 24317
    Prev
    Next
    INDEX
    Explanations

    if it

    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
     _______,
    -0.08
    ãĢij,
    -0.08
     infatti
    -0.08
     ÙģØ¥ÙĨ
    -0.08
    æĸ°åĬłåĿ¡
    -0.08
     ÙģØ¥ÙĨÙĩ
    -0.08
    retti
    -0.08
    èµ·è§ģ
    -0.08
    aeda
    -0.07
    erma
    -0.07
    POSITIVE LOGITS
    å®ĥ们æĺ¯
    0.09
    "';
    0.07
    å®ĥä»¬åľ¨
    0.07
     dibandingkan
    0.07
    ä¸Ĭæĸ°åı°éĺ¶
    0.07
    å®ĥæĺ¯
    0.07
    çļĦ人äºĨ
    0.07
    rames
    0.06
     compared
    0.06
     it
    0.06
    Activations Density 0.332%

    No Known Activations