© 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. 10750
    Prev
    Next
    INDEX
    Explanations

    character classification

    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
    åīįä¸ĸ
    -0.07
    ple
    -0.07
    au
    -0.07
    aum
    -0.07
    nap
    -0.07
    verg
    -0.07
     höh
    -0.07
    æĺ¥åħī
    -0.07
    |min
    -0.07
    çŃīçĿĢä½ł
    -0.07
    POSITIVE LOGITS
    gnore
    0.08
    iguous
    0.07
    æĹ¥åł±
    0.07
     jointly
    0.06
    erate
    0.06
    Coupon
    0.06
     ourselves
    0.06
    wali
    0.06
    æŃ£ä¸Ń
    0.06
    ISM
    0.06
    Activations Density 0.003%

    No Known Activations