© 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. 22337
    Prev
    Next
    INDEX
    Explanations

    to investigate/assess/examine/determine

    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
    è°ģæĿ¥
    -0.08
    ontology
    -0.08
    WORDS
    -0.08
    intér
    -0.07
    relude
    -0.07
    SCALE
    -0.07
    åŃ½
    -0.07
    lamour
    -0.07
    stdlib
    -0.07
    ç½
    -0.07
    POSITIVE LOGITS
     accordingly
    0.08
    iko
    0.07
     therefore
    0.07
    åĽłæŃ¤åľ¨
    0.07
    pany
    0.07
    两çĶ¨
    0.06
    纫
    0.06
    ko
    0.06
    mit
    0.06
    æıIJä¾ĽæĽ´
    0.06
    Activations Density 0.011%

    No Known Activations