© 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. 43636
    Prev
    Next
    INDEX
    Explanations

    chlorophyll

    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
    游走
    -0.08
    è¿ĩæĿ¥çļĦ
    -0.07
    骨èĤī
    -0.07
     antibio
    -0.07
    åı¯ä»¥èĢĥèĻij
    -0.07
    obody
    -0.07
    èĬ±å²Ĺ
    -0.07
    ä¸īéĥ¨æĽ²
    -0.07
    æİ
    -0.07
    éĴŁæĥħ
    -0.07
    POSITIVE LOGITS
    éķ°
    0.08
    è¶ĬåĨ¬
    0.07
    LESS
    0.07
    aeda
    0.07
    åIJĦ级
    0.07
    ool
    0.07
    -green
    0.07
    é»Ħç´ł
    0.07
     hues
    0.06
    hér
    0.06
    Activations Density 0.016%

    No Known Activations