© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56921
    Prev
    Next
    INDEX
    Explanations

    removing from lists

    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
    æīĵãģ¡
    -0.08
     sourceMapping
    -0.08
    交åıī
    -0.08
    ä¸įå½Ĵ
    -0.07
    ncy
    -0.07
    æĬķåIJij
    -0.07
     Pig
    -0.07
    rike
    -0.07
    WORK
    -0.07
    master
    -0.07
    POSITIVE LOGITS
     removal
    0.09
    æŁ¥çľĭæĽ´å¤ļ
    0.08
    çļĤ
    0.08
     retrieves
    0.08
     operation
    0.08
     retrieval
    0.07
    peek
    0.07
     retrieving
    0.07
     Removal
    0.07
     Removes
    0.07
    Activations Density 0.048%

    No Known Activations