© 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. 61401
    Prev
    Next
    INDEX
    Explanations

    0 or null values

    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
    ê·¼
    -0.07
    ä¸Ģå¦ĤæĹ¢å¾Ģåľ°
    -0.07
    olan
    -0.07
    åĵ¥
    -0.06
     kir
    -0.06
     magn
    -0.06
    estre
    -0.06
    åŁ¹åħ»åŃ©åŃIJçļĦ
    -0.06
    .pol
    -0.06
    lau
    -0.06
    POSITIVE LOGITS
    ä¹Łä¸įåĨį
    0.09
    ä¸įåĨį
    0.09
    å½»åºķ
    0.08
    ä¸ĢæŦ
    0.08
    åĨįä¹Łä¸į
    0.08
    ä¸įåĨįæľī
    0.08
     definitiva
    0.08
     definitivo
    0.08
    æ°¸ä¹ħ
    0.08
     наконеÑĨ
    0.08
    Activations Density 0.004%

    No Known Activations