© 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. 2717
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming constructs

    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
    lian
    -0.07
    udo
    -0.06
    ello
    -0.06
    ikin
    -0.06
     Alv
    -0.06
    ilor
    -0.06
     Kear
    -0.06
    åĤ¨
    -0.06
    kinson
    -0.06
    临åħ¶
    -0.06
    POSITIVE LOGITS
    atria
    0.08
    nested
    0.08
     belas
    0.08
    utches
    0.08
    åĽ½åĨħå¸Ĥåľº
    0.08
    szak
    0.08
     nested
    0.08
    ĽĦ
    0.08
    åħ´
    0.07
    ήμε
    0.07
    Activations Density 0.004%

    No Known Activations