© 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. 23400
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or programming code 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
    ئÙĦ
    -0.07
    åĤħ
    -0.07
    éģĵçIJĨçļĦ
    -0.07
    ä¸įæ²»
    -0.07
     Idee
    -0.07
     ÙħÙĨظÙĪر
    -0.07
    posito
    -0.07
    unki
    -0.07
    .plan
    -0.07
    大åĬ¿
    -0.07
    POSITIVE LOGITS
     Engel
    0.07
    hen
    0.07
    зан
    0.06
     definite
    0.06
     Maher
    0.06
    éĥ½æľīäºĨ
    0.06
    驹
    0.06
    çıŃä¸Ĭ
    0.06
    ÐĤ
    0.06
    ongo
    0.06
    Activations Density 0.001%

    No Known Activations