© 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. 63776
    Prev
    Next
    INDEX
    Explanations

    partition, dp-finite, mathematical notation

    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
    quetes
    -0.08
    akis
    -0.08
    æŀī
    -0.08
    ä¸ĢåĨį
    -0.08
    æĥħæĦı
    -0.08
    ç±³ç²ī
    -0.08
     Nuc
    -0.08
     sigmoid
    -0.08
    /posts
    -0.08
    pekt
    -0.07
    POSITIVE LOGITS
     random
    0.08
     pathological
    0.08
    ä¹±
    0.08
     Conway
    0.07
     constructed
    0.07
     constructions
    0.07
     exotic
    0.07
    Constructed
    0.07
    æŀģ端
    0.07
    å°ĸ
    0.07
    Activations Density 0.014%

    No Known Activations