© 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. 8226
    Prev
    Next
    INDEX
    Explanations

    findings suggest

    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
     Enter
    -0.07
     forever
    -0.07
    angu
    -0.07
    éªı
    -0.06
    á»ĵi
    -0.06
     certas
    -0.06
    åŁºæľ¬è¦ģæ±Ĥ
    -0.06
     enter
    -0.06
     Always
    -0.06
    Originally
    -0.06
    POSITIVE LOGITS
     corrobor
    0.10
    åı¯èĥ½æĺ¯åĽłä¸º
    0.09
     AUTHORS
    0.08
    ä¸Ĭè¿°äºĭå®ŀ
    0.08
    /devices
    0.08
    以å®ŀéĻħè¡ĮåĬ¨
    0.08
    åģļä¸ĢåIJį
    0.07
    åľ¨ä»ĬåIJİçļĦ
    0.07
    åı¯èĥ½ä¸İ
    0.07
    该åĮº
    0.07
    Activations Density 0.243%

    No Known Activations