© 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. 11224
    Prev
    Next
    INDEX
    Explanations

    TOM BRADY

    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
    ":"/
    -0.07
    amodel
    -0.07
    æ¡ij
    -0.07
    asang
    -0.07
    èĽ¾
    -0.07
    ä¸Ģæ¡£
    -0.07
     retra
    -0.07
     //////////////////
    -0.07
    ä¸Ģä½ĵæľº
    -0.07
    庸
    -0.07
    POSITIVE LOGITS
    æĺ¯åĢ¼å¾Ĺ
    0.06
    éľĸ
    0.06
    uku
    0.06
    åįİé¾Ļ
    0.06
    gaard
    0.06
    ucha
    0.06
    ga
    0.06
    ì§ĢëĬĶ
    0.06
    оÑī
    0.06
    åĨ³èĥľ
    0.06
    Activations Density 0.011%

    No Known Activations