© 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. 46658
    Prev
    Next
    INDEX
    Explanations

    referring to text below

    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
    addin
    -0.08
    æľĢåIJİä¸Ģ天
    -0.08
    anke
    -0.08
    æľ¬çīĩ
    -0.08
     Ùħؤخ
    -0.07
    andar
    -0.07
    /**<
    -0.07
    Ïīμα
    -0.07
    ivio
    -0.07
    itial
    -0.07
    POSITIVE LOGITS
    æĽ´ç²¾å½©
    0.07
     below
    0.07
    adays
    0.07
    æīĢ示
    0.07
    :
    0.07
    below
    0.07
     ниже
    0.07
    लि
    0.06
    est
    0.06
    骤
    0.06
    Activations Density 0.112%

    No Known Activations