© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23086
    Prev
    Next
    INDEX
    Explanations

    list separators and booleans

    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
    íĸ¥
    -0.07
    äºĭä¸ļåįķä½įåħ¬å¼ĢæĭĽèģĺ
    -0.07
    deen
    -0.07
    rite
    -0.07
    涵
    -0.07
    ombat
    -0.07
    aign
    -0.07
    Ĥ¬
    -0.07
    ©
    -0.07
    æĽ¸åºĹ
    -0.07
    POSITIVE LOGITS
    纵
    0.07
    ubl
    0.07
    idem
    0.07
    ib
    0.07
     Gang
    0.07
    ifax
    0.07
    æĮijèµ·
    0.06
     Microsystems
    0.06
    etter
    0.06
     pac
    0.06
    Activations Density 0.069%

    No Known Activations