© 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. 24068
    Prev
    Next
    INDEX
    Explanations

    fish, fruit, butter, spreads

    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¨ģ士å¿Į
    -0.07
    奶èĮ¶
    -0.06
     mortal
    -0.06
    æĢ§æł¼
    -0.06
    èį¯åīĤ
    -0.06
    &action
    -0.06
    ç½®
    -0.06
    çĶŁæŃ»
    -0.06
    éħĴçļĦ
    -0.06
    éħĴçĵ¶
    -0.06
    POSITIVE LOGITS
    éĢĤéĩı
    0.10
    æĽ¿ä»£åĵģ
    0.09
    å¯ĮåIJ«
    0.09
    TTY
    0.09
    åIJ«æľīçļĦ
    0.09
    ä¸įåIJ«
    0.08
    åIJ«
    0.08
    åIJ«æľī丰å¯ĮçļĦ
    0.08
    åIJ«æľī
    0.08
    ç±»åĴĮ
    0.08
    Activations Density 0.025%

    No Known Activations