© 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. 17723
    Prev
    Next
    INDEX
    Explanations

    so what

    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
    ease
    -0.08
    å¾Ī容æĺĵ
    -0.08
    Ĺı
    -0.08
    евÑģкого
    -0.08
    cope
    -0.08
    ives
    -0.08
    zey
    -0.08
    quilla
    -0.08
    å¾Īå¤ļä¸ľè¥¿
    -0.07
    tyw
    -0.07
    POSITIVE LOGITS
    究竣
    0.09
    åĪ°åºķæĺ¯
    0.09
    åĪ°åºķ
    0.09
     what
    0.08
    究竣æĺ¯
    0.08
    åĪ°åºķæĺ¯ä»Ģä¹Ī
    0.08
    ä½łåĪ°åºķ
    0.08
    åĪ°åºķæľīå¤ļ
    0.07
    What
    0.07
     basically
    0.07
    Activations Density 0.151%

    No Known Activations