© 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. 43103
    Prev
    Next
    INDEX
    Explanations

    bioassay-derived equivalents

    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
     dialect
    -0.07
    åħ´è¶£
    -0.07
    èµ·æĿ¥åIJ§
    -0.07
    adel
    -0.07
    Helpers
    -0.07
    Hooks
    -0.06
    ãi
    -0.06
    axed
    -0.06
    WithError
    -0.06
    说åIJ§
    -0.06
    POSITIVE LOGITS
    izr
    0.08
    计ç®Ĺåĩº
    0.08
    éĺ»
    0.08
    ritz
    0.07
     emas
    0.07
    æıĴ
    0.07
    æľĢå¿«çļĦéĢŁåº¦
    0.07
    anat
    0.07
    åĪij
    0.07
    ç¼ļ
    0.07
    Activations Density 0.004%

    No Known Activations