© 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. 19636
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with operators

    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
    èİ«åIJįçļĦ
    -0.08
    arcy
    -0.07
    roys
    -0.07
    é«ĺçŃīä¸ĵç§ijåŃ¦æł¡
    -0.07
    ä¸Ĭ人
    -0.06
    upal
    -0.06
    errat
    -0.06
    åĪĽæĸ°æĦıè¯Ĩ
    -0.06
    åĦŁ
    -0.06
    Registrar
    -0.06
    POSITIVE LOGITS
    enet
    0.07
    åī¯
    0.06
    issa
    0.06
    严å®Ī
    0.06
    ãĥĦ
    0.06
    åħ¨ä½ĵ
    0.06
    agram
    0.06
     real
    0.06
    æ¢
    0.06
    za
    0.06
    Activations Density 0.062%

    No Known Activations