© 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. 39094
    Prev
    Next
    INDEX
    Explanations

    AzPainter software

    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
    ä¸įçĶŁ
    -0.06
     Grip
    -0.06
     Inf
    -0.06
     inf
    -0.06
    usal
    -0.06
    uz
    -0.06
    好æĪIJ绩
    -0.05
    Unchecked
    -0.05
    æŁ¿
    -0.05
    æ°ĹåĪĨ
    -0.05
    POSITIVE LOGITS
    atat
    0.09
    çĻ»è®°è¯ģ
    0.09
    errat
    0.08
    æŁ¥çľĭåħ¨æĸĩ
    0.08
    ught
    0.08
    ловиÑĩ
    0.08
    请èĢIJå¿ĥçŃīå¾ħ
    0.08
    outine
    0.08
    olata
    0.08
    èĩªå·±è¢«
    0.08
    Activations Density 0.001%

    No Known Activations