© 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. 49143
    Prev
    Next
    INDEX
    Explanations

    measuring concentration in a liquid

    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
    ail
    -0.08
    ific
    -0.07
    issement
    -0.07
    使ãģĨ
    -0.07
    ey
    -0.07
    æĥŁä¸Ģ
    -0.07
    æĪijè¦ģè¯Ħ论
    -0.07
    è¶ĬãģĹ
    -0.07
    æĪIJç»©æŁ¥è¯¢
    -0.07
    ä¸ĭ载次æķ°
    -0.07
    POSITIVE LOGITS
    -www
    0.08
     given
    0.08
    æł·æľ¬
    0.07
     sample
    0.07
    æķ´ä¸ª
    0.07
    gan
    0.06
    sample
    0.06
    nier
    0.06
     SAMPLE
    0.06
    ç»Ļå®ļ
    0.06
    Activations Density 0.154%

    No Known Activations