© 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. 12927
    Prev
    Next
    INDEX
    Explanations

    retention of behaviour

    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
    oriously
    -0.09
    urnal
    -0.09
     ë¶ĢíĦ°
    -0.09
    ลฯ
    -0.08
    мога
    -0.08
    entimes
    -0.08
    uality
    -0.08
    eenth
    -0.08
    rollo
    -0.08
    olla
    -0.08
    POSITIVE LOGITS
    OrUpdate
    0.09
    ä¸įä½ı
    0.08
    ä¸įä½ıäºĨ
    0.08
    åĴĮåĪ©çĶ¨
    0.07
    åĴĮåıijå±ķ
    0.07
    ä¸įä½ıçļĦ
    0.07
    ä¸ĭæĿ¥çļĦ
    0.07
    æĥķ
    0.07
    ä¸įæĭĶ
    0.07
    ist
    0.07
    Activations Density 0.047%

    No Known Activations