© 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. 31244
    Prev
    Next
    INDEX
    Explanations

    Kensington Mouse, babysitting, Pontiac, mangrove, Monk, World Cup

    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
    eves
    -0.06
    ibilities
    -0.06
    ä¸Ģ
    -0.06
    åĢ
    -0.06
    è¨Ģ
    -0.06
    -threat
    -0.06
    éĿĴ
    -0.06
    éģĹæĨ¾çļĦæĺ¯
    -0.06
    æĢ§åıĬ
    -0.05
    ä¸ĢæıIJ
    -0.05
    POSITIVE LOGITS
    ิà¹Īà¸ĩ
    0.08
    ãģłãģĭãĤīãģĵãģĿ
    0.07
    ЧС
    0.07
    æľ¬ç«ĻåĨħ容
    0.07
    äºĮè¦ģ
    0.07
    á»ıng
    0.07
    inos
    0.07
    çĶ·çļĦ
    0.07
    åij¦
    0.07
    .rl
    0.07
    Activations Density 0.035%

    No Known Activations