© 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. 63804
    Prev
    Next
    INDEX
    Explanations

    size of communicator

    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
    icca
    -0.09
    絡
    -0.08
    补课
    -0.08
    ä¿Ŀ驾
    -0.08
    åĬ¡å·¥
    -0.07
    âĺĨâĺĨ
    -0.07
    ÏĨοÏģά
    -0.07
    çŧ
    -0.07
    utters
    -0.07
    è·¯æĺĵæĸ¯
    -0.07
    POSITIVE LOGITS
    æĹłåīį
    0.07
    erche
    0.07
     hypo
    0.07
    usal
    0.06
    peg
    0.06
     sole
    0.06
    esch
    0.06
    ؤ
    0.06
    rou
    0.06
     Edelst
    0.06
    Activations Density 0.020%

    No Known Activations