© 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. 33640
    Prev
    Next
    INDEX
    Explanations

    he/she/it/they verb

    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
    综ä¸Ĭ
    -0.08
    ordial
    -0.08
    天ä½ij
    -0.07
    queira
    -0.06
    ây
    -0.06
    ÄįiÄĩ
    -0.06
    ãĥĢãĥł
    -0.06
     HuffPost
    -0.06
    arte
    -0.06
     [{'
    -0.06
    POSITIVE LOGITS
    ç³»ç»Łåľ°
    0.08
    oned
    0.08
    ©
    0.07
    æľ¬èº«å°±æĺ¯
    0.07
    onel
    0.07
    yc
    0.07
    oz
    0.07
    èĩªèº«çļĦ
    0.07
    ä»Ģä¹Īæł·
    0.07
    èĢĥçĶŁçļĦ
    0.07
    Activations Density 0.306%

    No Known Activations