© 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. 9542
    Prev
    Next
    INDEX
    Explanations

    chiral, handed, lateral, helical

    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
    æĺ¯éĽĨ
    -0.07
     plur
    -0.07
    èĮĥåĽ´
    -0.07
    ä¸Ģ鸣
    -0.06
    æĬ¥
    -0.06
    çģ«åĢĻ
    -0.06
    ModelError
    -0.06
    ologna
    -0.06
    _ELEMENTS
    -0.06
    èķ
    -0.06
    POSITIVE LOGITS
    criptor
    0.08
    designation
    0.08
    /angular
    0.08
    .sendMessage
    0.08
    isky
    0.08
    irian
    0.08
    degrees
    0.08
     stripe
    0.08
    é£İæµģ
    0.08
    confirmed
    0.07
    Activations Density 0.001%

    No Known Activations