© 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. 26797
    Prev
    Next
    INDEX
    Explanations

    shard computing

    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
    empa
    -0.08
    proc
    -0.08
    æĽľ
    -0.08
    Ŀ
    -0.08
    koli
    -0.07
    alak
    -0.07
    oston
    -0.07
     láng
    -0.07
    uple
    -0.07
    etak
    -0.07
    POSITIVE LOGITS
    sing
    0.07
    it
    0.07
    itz
    0.07
    éģĵçIJĨ
    0.06
    å¼ķ
    0.06
    arding
    0.06
    ito
    0.06
    orum
    0.06
    ait
    0.06
     sing
    0.06
    Activations Density 0.536%

    No Known Activations