© 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. 21870
    Prev
    Next
    INDEX
    Explanations

    insufficiency, deficiency, pain, fever, caused

    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
    boh
    -0.07
    æĽ¿ä½ł
    -0.07
    çŃīæݪæĸ½
    -0.07
    æĽ´ç²¾å½©
    -0.07
    åĶ¾
    -0.07
    æľĢèµ·çłģ
    -0.07
     aldrig
    -0.07
     intensiv
    -0.06
    ifr
    -0.06
    çļĦæĬĢå·§
    -0.06
    POSITIVE LOGITS
    éĤ£ç§į
    0.09
    导èĩ´çļĦ
    0.09
     hyp
    0.08
    hyper
    0.08
    é¡½åĽº
    0.08
    å¼ķèµ·çļĦ
    0.08
    isman
    0.08
     caused
    0.07
    hyp
    0.07
    éĹŃå¡ŀ
    0.07
    Activations Density 0.044%

    No Known Activations