© 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. 55740
    Prev
    Next
    INDEX
    Explanations

    assumed or expected outcomes

    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
    æıīäºĨ
    -0.08
    áĥ£áĥľ
    -0.08
    åĴĮç¾İ
    -0.08
    обоÑĢоÑĤ
    -0.08
    ä¸īè¦ģ
    -0.08
    <|box_end|>
    -0.08
    rement
    -0.08
    ả
    -0.07
    天å¿ĥ
    -0.07
    åĭĻ
    -0.07
    POSITIVE LOGITS
    æĮīçIJĨ
    0.09
    —but
    0.08
    âĢ¦but
    0.08
    好äºĨ
    0.07
    ä¼łç»Ł
    0.07
    ä½Ĩè¿Ļ
    0.07
     theoretically
    0.07
    .But
    0.07
    èĪ
    0.07
     tempting
    0.07
    Activations Density 0.271%

    No Known Activations