© 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. 48069
    Prev
    Next
    INDEX
    Explanations

    special characters or names

    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
    nya
    -0.15
    ly
    -0.11
    ELY
    -0.10
    nout
    -0.10
    ÑĮÑı
    -0.09
    ÑģÑı
    -0.09
    ezza
    -0.09
    à¸Ĺรà¹Į
    -0.09
    оÑģÑĮ
    -0.09
    maa
    -0.09
    POSITIVE LOGITS
    ©
    0.09
    i
    0.09
    zelfde
    0.07
    ãģ³
    0.07
    bé
    0.07
    it
    0.07
    ar
    0.07
    ìĬ¤ëŁ½ê²Į
    0.06
    и
    0.06
    -même
    0.06
    Activations Density 0.018%

    No Known Activations