© 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. 57145
    Prev
    Next
    INDEX
    Explanations

    sigma70, Manufacturer, Ruby, /php

    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
    accio
    -0.07
     몰
    -0.07
     Miser
    -0.06
    matic
    -0.06
    acci
    -0.06
    å§ĭ
    -0.06
    åĴĮåĪĺ
    -0.06
    cir
    -0.06
    ail
    -0.06
    Ха
    -0.06
    POSITIVE LOGITS
    {}_
    0.08
    еÑīа
    0.07
    еÑĩи
    0.07
    ybrid
    0.07
    详ç»Ĩåľ°åĿĢ
    0.07
    ensburg
    0.07
    ربÛĮ
    0.07
    ãĤıãĤĬãģ«
    0.07
    ç¥ŀä¹ĭ
    0.07
    ÑĥÑĢг
    0.07
    Activations Density 0.168%

    No Known Activations