© 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. 10726
    Prev
    Next
    INDEX
    Explanations

    you want/did/can/are

    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
    ñas
    -0.07
    undu
    -0.07
    ä¸Ģ票
    -0.07
    ä¸Ģçľ¼
    -0.07
     recom
    -0.07
     newcomer
    -0.06
     дÑĥ
    -0.06
     Verz
    -0.06
    ä¹Łä¸įæĥ³
    -0.06
    è¯ķ
    -0.06
    POSITIVE LOGITS
    alloc
    0.07
     geh
    0.07
    ellini
    0.07
    ugel
    0.07
    .obtain
    0.07
    à¸Ŀà¹Īา
    0.07
    .adapters
    0.07
    à©
    0.07
    /js
    0.07
    _adapter
    0.07
    Activations Density 0.002%

    No Known Activations