© 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. 33569
    Prev
    Next
    INDEX
    Explanations

    high yield and purity

    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
    å¸ĮæľĽåı¯ä»¥
    -0.08
    acap
    -0.08
    ä¼Ĺ
    -0.08
    ä½łæĪij
    -0.07
    åĸĦæģ¶
    -0.07
    å¿ħèĥľ
    -0.07
    å¹³åĥ¹
    -0.07
    ÐĵС
    -0.07
    é
    -0.07
    ä¸ĩ亿
    -0.07
    POSITIVE LOGITS
     recovered
    0.08
     purity
    0.08
    纯åĮĸ
    0.08
     weighed
    0.07
    æİĸ
    0.07
     полÑĥÑĩен
    0.07
     morphology
    0.07
    ä¸Ńéĸĵ
    0.07
    ç»ĵæĻ¶
    0.07
    ières
    0.07
    Activations Density 0.047%

    No Known Activations