© 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. 43399
    Prev
    Next
    INDEX
    Explanations

    numbers and English words

    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
    赡
    -0.07
    èIJ¥éĢłäºĨ
    -0.07
    iej
    -0.06
    uces
    -0.06
    iciel
    -0.06
    osz
    -0.06
     Kör
    -0.06
    ösen
    -0.06
    heim
    -0.06
    ütz
    -0.06
    POSITIVE LOGITS
    AMAN
    0.09
    mog
    0.08
    éľ²æ°´
    0.08
    æľĢæľīæķĪ
    0.07
    åħ¥éĩij
    0.07
    æİĴä½į
    0.06
    elve
    0.06
    -results
    0.06
    enan
    0.06
    é¢Ħ
    0.06
    Activations Density 0.043%

    No Known Activations