© 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. 22951
    Prev
    Next
    INDEX
    Explanations

    numbers and letter sequences

    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
    并ç»ĵåIJĪ
    -0.08
    gin
    -0.07
    ÑĪел
    -0.06
    oue
    -0.06
    åħ·
    -0.06
    iva
    -0.06
    .Sockets
    -0.06
    cq
    -0.06
     Space
    -0.06
    #:
    -0.06
    POSITIVE LOGITS
    ç¿¡
    0.08
     enfin
    0.08
    åį¡ç½Ĺ
    0.07
    AppBundle
    0.07
    Fabr
    0.07
    alma
    0.07
    æĽ´çĶŁ
    0.07
    appiness
    0.07
     Servi
    0.07
    ecer
    0.07
    Activations Density 0.002%

    No Known Activations