© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56293
    Prev
    Next
    INDEX
    Explanations

    _epi

    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
    ÖĢ
    -0.08
    ר×Ķ
    -0.08
    åĴĮåŁ¹åħ»
    -0.08
    /change
    -0.07
     ene
    -0.07
    /respond
    -0.07
    leigh
    -0.07
    dene
    -0.07
    lest
    -0.07
    лив
    -0.07
    POSITIVE LOGITS
    udson
    0.07
    ç»´åħĭ
    0.06
    åį¡ç½Ĺ
    0.06
    èĩ´è¿ľ
    0.06
    çīĪ车åŀĭ
    0.06
    çīĽ
    0.06
    ãģĦãģĭãģĮ
    0.06
    æĭĶæ²³
    0.06
     légère
    0.06
     larga
    0.06
    Activations Density 0.010%

    No Known Activations