© 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. 24176
    Prev
    Next
    INDEX
    Explanations

    mockit phrases and sanders

    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
    æĿ¡æĿ¡
    -0.07
    Č↵
    -0.07
     Gente
    -0.07
    è¿İ
    -0.07
    iber
    -0.06
    iller
    -0.06
    ÑĤком
    -0.06
    ä¸ŃçŃ¾
    -0.06
    æ³
    -0.06
    }):
    -0.06
    POSITIVE LOGITS
    åĪĨ
    0.07
    ipa
    0.07
    Äħż
    0.07
    áĢĦ
    0.07
    inaire
    0.07
    vara
    0.06
    okr
    0.06
     Hindu
    0.06
    etty
    0.06
    hun
    0.06
    Activations Density 0.008%

    No Known Activations