© 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. 33182
    Prev
    Next
    INDEX
    Explanations

    set/edit route and free gift

    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
    plevel
    -0.06
    affe
    -0.06
     Bair
    -0.06
    atri
    -0.06
     caut
    -0.06
    人为
    -0.06
    ä¹ĭåīij
    -0.06
    enz
    -0.06
    eru
    -0.06
    ASE
    -0.06
    POSITIVE LOGITS
    åıĭ好çļĦ
    0.08
    æĪijæĿ¥è¯´ä¸¤åı¥
    0.08
    vince
    0.08
    wan
    0.07
    ico
    0.07
    大ä¸ĸçķĮ
    0.07
    alth
    0.07
    ÑĢам
    0.07
    们éĥ½
    0.07
    çĶŁç´ł
    0.07
    Activations Density 0.619%

    No Known Activations