© 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. 31060
    Prev
    Next
    INDEX
    Explanations

    names or proper nouns

    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
    æ¸ħéĨĴ
    -0.07
     progrès
    -0.07
    scaled
    -0.07
    avi
    -0.07
     scaled
    -0.07
    گاÙĨ
    -0.07
     пÑĢогÑĢ
    -0.07
    èĩªç¼ĸ
    -0.07
    idar
    -0.07
    åĨįè¿ĩ
    -0.07
    POSITIVE LOGITS
    atak
    0.08
     reluctantly
    0.08
    å¿ĥçĶĺæĥħæĦ¿
    0.07
    isko
    0.07
    ripe
    0.07
    ä¸įæĶ¹
    0.07
    åĢ¾åIJij
    0.07
     Ñģклон
    0.07
    åĢ¾åIJijäºİ
    0.07
    ادÙĨ
    0.07
    Activations Density 0.001%

    No Known Activations