© 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. 41774
    Prev
    Next
    INDEX
    Explanations

    special characters or separators

    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
    /spec
    -0.09
     поÑĩе
    -0.07
    ewe
    -0.07
    تÙĪÙĨ
    -0.07
    ewa
    -0.07
    /ion
    -0.07
    ekar
    -0.07
    renched
    -0.07
    ông
    -0.06
    ุม
    -0.06
    POSITIVE LOGITS
    anes
    0.08
    ikian
    0.07
    Configurer
    0.07
     brind
    0.07
    atings
    0.07
    åİ»æī¾
    0.07
    ippi
    0.06
    ijan
    0.06
    illo
    0.06
    æŀ
    0.06
    Activations Density 0.018%

    No Known Activations