© 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. 21545
    Prev
    Next
    INDEX
    Explanations

    list, ID, Oracle

    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
    ائÙĬ
    -0.06
    身临åħ¶å¢ĥ
    -0.06
    æī©å±ķèµĦæĸĻ
    -0.06
    onal
    -0.06
    trx
    -0.06
    项è§Ħå®ļ
    -0.06
     typings
    -0.06
    wth
    -0.06
    ienio
    -0.06
    å¼ģ
    -0.06
    POSITIVE LOGITS
    ayne
    0.08
    amana
    0.08
    èĢģ人家
    0.07
    ลà¹Į
    0.06
     STDERR
    0.06
    Ùİ
    0.06
    Sampler
    0.06
    Ùı
    0.06
    emente
    0.06
    koord
    0.06
    Activations Density 1.368%

    No Known Activations