© 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. 39444
    Prev
    Next
    INDEX
    Explanations

    age range

    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
    =('
    -0.07
    æį¢åı¥è¯Ŀ说
    -0.07
    erma
    -0.07
    วà¸ĩ
    -0.06
    Ùį
    -0.06
    ixe
    -0.06
     seguintes
    -0.06
    {/
    -0.06
     timespec
    -0.06
    doi
    -0.06
    POSITIVE LOGITS
    ç«ĭåį³ä¸ĭè½½
    0.08
     –,
    0.08
    è¦ģä¹Ī
    0.08
    è¿ijå¹³
    0.08
    warts
    0.07
    è¦ģä¹Īæĺ¯
    0.07
    kent
    0.07
    ä¸Ģæĺ¯
    0.07
    ruh
    0.07
    اث
    0.07
    Activations Density 0.028%

    No Known Activations