© 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. 33562
    Prev
    Next
    INDEX
    Explanations

    context and circumstance

    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
    è°¢è°¢ä½łä»¬
    -0.08
    åĪļ
    -0.07
    ³
    -0.07
    åħĭç¦ı
    -0.07
    enticator
    -0.06
    åĽłä¸ºåľ¨
    -0.06
    Ŀ
    -0.06
    åľ
    -0.06
    bidden
    -0.06
    peater
    -0.06
    POSITIVE LOGITS
    èĥĮæĻ¯ä¸ĭ
    0.10
    åīįæıIJä¸ĭ
    0.09
    åĩºä¸Ģéģĵ
    0.09
    æľīå¿ħè¦ģ
    0.08
    ftar
    0.07
    æĽ´éľĢè¦ģ
    0.07
    汹汹
    0.07
     λοι
    0.07
    æĽ´ä½ķåĨµ
    0.07
     question
    0.07
    Activations Density 0.055%

    No Known Activations