© 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. 10317
    Prev
    Next
    INDEX
    Explanations

    calidad, étrangera, peruana, correta, fechar, italiana

    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
    çŁ¥éĿĴ
    -0.08
    æĢĿæºIJ
    -0.07
    áĥIJáĥ¡
    -0.07
    жнее
    -0.07
    filer
    -0.07
    umen
    -0.07
    mada
    -0.07
     Merkezi
    -0.07
    bite
    -0.07
    ìī½
    -0.07
    POSITIVE LOGITS
    itud
    0.07
    ималÑĮ
    0.07
     بÙĪدÙĨ
    0.07
    ä¸Ĭ人
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    ud
    0.07
    以ä¸Ĭ
    0.06
    unar
    0.06
     carr
    0.06
    彪
    0.06
    Activations Density 0.036%

    No Known Activations