© 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. 4158
    Prev
    Next
    INDEX
    Explanations

    pumped-storage

    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
    <|box_end|>
    -0.09
    èĢĮ代ä¹ĭ
    -0.08
    çł´æµª
    -0.08
    ëĦĺ
    -0.08
    åİĨåı²åĴĮ
    -0.08
    ä»»ä½ķåħ¶ä»ĸ
    -0.08
    adow
    -0.08
    /design
    -0.08
    ละà¸Ħร
    -0.07
    ahu
    -0.07
    POSITIVE LOGITS
    çļĦ
    0.10
    hips
    0.10
    å¼ıçļĦ
    0.09
    ãĢģ
    0.09
    èĪ¬çļĦ
    0.09
    å¼ı
    0.08
    å¨ħ
    0.08
    ми
    0.08
    ï¼Ī
    0.08
    ات
    0.07
    Activations Density 0.011%

    No Known Activations