© 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. 65412
    Prev
    Next
    INDEX
    Explanations

    H2O2

    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
    èĩ´çļĦ
    -0.09
    hode
    -0.07
    avig
    -0.07
    à¹Ĩ
    -0.07
    isky
    -0.07
    åIJĦç§įåİŁåĽł
    -0.07
    еÑĤа
    -0.07
    -six
    -0.07
    czy
    -0.06
    ¬ģ
    -0.06
    POSITIVE LOGITS
    apter
    0.07
    ר×ķת
    0.07
    มà¸ĵà¹Į
    0.07
    çıŃéĽĨä½ĵ
    0.07
    åºĹéķĩ
    0.07
    @\
    0.07
     **ãĢĮ
    0.07
    ä¹ĻåıĮæĸ¹
    0.07
    gow
    0.07
    бол
    0.07
    Activations Density 0.008%

    No Known Activations