© 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. 20454
    Prev
    Next
    INDEX
    Explanations

    numerical sequences or lists

    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
    éĩįçĶŁä¹ĭ
    -0.09
    è¡ĮçŁ¥
    -0.07
    aul
    -0.07
    @g
    -0.07
    stech
    -0.07
    Ïģή
    -0.07
    uard
    -0.06
    riture
    -0.06
    oola
    -0.06
    Globals
    -0.06
    POSITIVE LOGITS
    enne
    0.07
    ouched
    0.07
    embr
    0.07
     Ips
    0.07
    èIJ½èIJ½
    0.06
     ÑĪÑĤÑĥ
    0.06
    itary
    0.06
    addy
    0.06
    çĦ¶
    0.06
    ÑĤеÑĢи
    0.06
    Activations Density 0.076%

    No Known Activations