© 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. 22496
    Prev
    Next
    INDEX
    Explanations

    XML/HTML closing tags and class definitions

    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
    ÉĻd
    -0.07
    uti
    -0.07
    åĬłåĪ©
    -0.07
    ä¸ĵçĶ¨åıij票
    -0.07
    麻辣çĥ«
    -0.07
    åIJ±
    -0.07
    ancis
    -0.07
    ulty
    -0.07
    æĢĴçģ«
    -0.06
    ssp
    -0.06
    POSITIVE LOGITS
    -bars
    0.07
     poo
    0.07
    ï¸İ
    0.07
    åıį
    0.07
    æ²īæ²ī
    0.07
    olla
    0.06
     Weston
    0.06
    PropertyChanged
    0.06
     perk
    0.06
     Seymour
    0.06
    Activations Density 0.002%

    No Known Activations