© 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. 7874
    Prev
    Next
    INDEX
    Explanations

    Prize, video, directive, Jacuzzi, reporter

    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
    .digest
    -0.08
    èĬ±èįī
    -0.07
    dera
    -0.07
    zak
    -0.07
    ulling
    -0.07
    .ssl
    -0.07
    _trees
    -0.07
    åħį
    -0.07
    å¤ı
    -0.07
    pira
    -0.07
    POSITIVE LOGITS
    izable
    0.08
    éĽĨä¸ŃéļĶ离
    0.07
    æīĢåľ¨ä½įç½®
    0.07
    apul
    0.07
    设æĸ½åĴĮ
    0.07
    atics
    0.06
     diri
    0.06
    æīĢæĮĩ
    0.06
    æĢ»ä¸įèĥ½
    0.06
    .currentTarget
    0.06
    Activations Density 0.013%

    No Known Activations