© 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. 20519
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    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
    ä¸į误
    -0.08
    Ī¬
    -0.08
    çݯ路
    -0.08
    дейÑģÑĤви
    -0.07
    allar
    -0.07
     ëį
    -0.07
    orat
    -0.07
     postale
    -0.07
    orning
    -0.07
    åĬªåĬĽçļĦ
    -0.07
    POSITIVE LOGITS
     Rosenstein
    0.07
    éĩijæĽ²
    0.06
    å±ķå¼Ģåħ¨æĸĩ
    0.06
    æŁĶ
    0.06
    лега
    0.06
    lef
    0.06
    inv
    0.06
    ä¸ĬåĬł
    0.06
    pector
    0.06
    ван
    0.05
    Activations Density 0.161%

    No Known Activations