© 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. 31973
    Prev
    Next
    INDEX
    Explanations

    Suisse Group, input file, MySQL

    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
    IRST
    -0.08
    éķ¿ç©º
    -0.07
    Opens
    -0.07
     ÐļÑĢаÑģи
    -0.07
    igate
    -0.07
     Jér
    -0.06
    åĶ¤
    -0.06
    ache
    -0.06
    çIJ³
    -0.06
     decorate
    -0.06
    POSITIVE LOGITS
    DD
    0.07
    èĬĿ
    0.07
    .echo
    0.07
    <<<
    0.07
    ש×ķ×ij
    0.07
    æ§ĥ
    0.07
     "---
    0.07
    permalink
    0.07
    .sd
    0.07
    gres
    0.07
    Activations Density 0.009%

    No Known Activations