© 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. 27503
    Prev
    Next
    INDEX
    Explanations

    code block delimiters and keywords

    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
    ÏĨη
    -0.06
    æĦıä¹īä¸ĬçļĦ
    -0.06
    ader
    -0.06
    tros
    -0.06
    /plain
    -0.06
    èĹ©
    -0.05
    å®ļçļĦ
    -0.05
    ़
    -0.05
    輩
    -0.05
    ä¾Ľ
    -0.05
    POSITIVE LOGITS
    Õ»
    0.08
    ListComponent
    0.08
    转载èĩ³
    0.07
    å¾Ĺ天çĭ¬
    0.07
    é»ŀæĪij
    0.07
    ConfigurationException
    0.07
    icientes
    0.07
    ç»ĵæŀĦ设计
    0.07
    åĨįæİ¥åĨįåİī
    0.07
    æľ¬æĸĩéĵ¾æİ¥
    0.07
    Activations Density 0.037%

    No Known Activations