© 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. 25443
    Prev
    Next
    INDEX
    Explanations

    parentheses or mathematical 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
    sel
    -0.07
    onn
    -0.07
     Podle
    -0.06
    æ¿
    -0.06
    ilo
    -0.06
    енÑĤи
    -0.06
    çĶļèĩ³è¿ŀ
    -0.06
    é¸¡æ¯Ľ
    -0.06
    ören
    -0.06
    oni
    -0.06
    POSITIVE LOGITS
    ajukan
    0.07
    faat
    0.07
    asure
    0.07
     voc
    0.07
    shade
    0.07
    -begin
    0.07
    åIJİåį³åı¯
    0.06
    arrer
    0.06
    측
    0.06
    าระ
    0.06
    Activations Density 0.024%

    No Known Activations