© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17747
    Prev
    Next
    INDEX
    Explanations

    malignancies

    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
    ç¼ĸ
    -0.08
    ersion
    -0.08
    pivot
    -0.07
    帯
    -0.07
    éĩĩæł·
    -0.07
    loquent
    -0.07
    arrant
    -0.07
    é¨İ士
    -0.07
    еÑĩениÑı
    -0.07
     обÑĢаÑĤиÑĤÑĮ
    -0.07
    POSITIVE LOGITS
    zas
    0.07
    _logging
    0.07
    ocht
    0.07
    WAR
    0.07
     Craw
    0.07
     petroleum
    0.07
    enaire
    0.07
    CRET
    0.07
    ADDING
    0.06
    åIJī
    0.06
    Activations Density 0.005%

    No Known Activations