© 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. 18944
    Prev
    Next
    INDEX
    Explanations

    Clark, Lewis, claim, caring

    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
    æľī两个
    -0.06
    ä¸Ńæĸ¹
    -0.06
     **
    -0.06
    è´¸
    -0.05
    "
    -0.05
    Ñİ
    -0.05
    an
    -0.05
    اÙĨÙĩ
    -0.05
    acter
    -0.05
    NR
    -0.05
    POSITIVE LOGITS
     risult
    0.08
    phia
    0.08
    éĥ¨çº§
    0.08
    ibrary
    0.08
     niá»ĩm
    0.08
    ecca
    0.08
    æľīåķ¥
    0.08
     Freitas
    0.08
    好æŃ¹
    0.08
    Õ©
    0.08
    Activations Density 0.001%

    No Known Activations