© 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. 13757
    Prev
    Next
    INDEX
    Explanations

    concerns or oversight

    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
    羣æľī
    -0.07
    æľīéģĵ
    -0.07
    æģ¢
    -0.07
    æľīåħ³æ³ķå¾ĭ
    -0.07
    åħ¶å®ĥ
    -0.06
    utore
    -0.06
    മാ
    -0.06
     waarmee
    -0.06
    åħ¶ä¸Ńæľī
    -0.06
    arked
    -0.06
    POSITIVE LOGITS
    âĢĮ
    0.10
    0.08
    âĢ
    0.07
    âĢİ
    0.06
     advancements
    0.06
    Dragging
    0.06
    以ä¸ĭæĺ¯ä¸ĢäºĽ
    0.06
    gando
    0.06
    ç©İ
    0.06
    halt
    0.06
    Activations Density 1.366%

    No Known Activations