© 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. 21488
    Prev
    Next
    INDEX
    Explanations

    choose or select

    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
     punc
    -0.08
    aney
    -0.08
    å±Ģéĥ¨çļĦ
    -0.07
    è¿ĶåĽŀ顶éĥ¨
    -0.07
    æģ¯çļĦ
    -0.07
    $header
    -0.07
    à¤Ĥà¤ķ
    -0.07
     late
    -0.07
    åħ·æľīçĭ¬ç«ĭ
    -0.07
    ead
    -0.07
    POSITIVE LOGITS
    åĭ¾éĢī
    0.10
     desired
    0.09
     chá»įn
    0.08
    éĢīæĭ©
    0.08
    åĭ¾
    0.08
     settings
    0.07
    设置为
    0.07
     ìĽIJíķĺëĬĶ
    0.07
    éĢī
    0.07
    åįķéĢī
    0.07
    Activations Density 0.150%

    No Known Activations