© 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. 1578
    Prev
    Next
    INDEX
    Explanations

    figures, Robert, perception, spirit, content

    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
    åĩŃåĢŁåħ¶
    -0.08
     خصÙĪص
    -0.07
    à¸ģระ
    -0.07
    enario
    -0.06
    æľĽçĿĢ
    -0.06
    åĪ
    -0.06
    apist
    -0.06
    两çĶ¨
    -0.06
    —including
    -0.06
    å¥ĭ
    -0.06
    POSITIVE LOGITS
    ä¸ĭ个
    0.07
    ä¸ĬåĬł
    0.07
    éĥ½çŁ¥éģĵ
    0.07
    æľĢæĸ°è¯Ħ论
    0.07
     moindre
    0.07
    åħ¶ä»ĸæĸ¹å¼ı
    0.06
    ä¸įæĹ©
    0.06
    åIJµæŀ¶
    0.06
    mour
    0.06
    вл
    0.06
    Activations Density 0.004%

    No Known Activations