© 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. 3416
    Prev
    Next
    INDEX
    Explanations

    Trustee, Guardian, Funds

    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
    åħ¬åı¸æĪIJåijĺ
    -0.08
    jukan
    -0.07
    stroy
    -0.07
    подоб
    -0.07
    éĢīè°ĥçĶŁ
    -0.07
    åħ¥èį·
    -0.07
    æľĢä½İåѦåİĨ
    -0.07
    注åĨĮåħ¬åı¸
    -0.07
    kaar
    -0.06
    _refs
    -0.06
    POSITIVE LOGITS
    åħ±è®¡
    0.09
     herein
    0.08
     pursuant
    0.08
    详è§ģ
    0.08
    åIJĮæĹ¥
    0.08
    æľīæķĪæľŁèĩª
    0.07
    举èĩ³
    0.07
    intang
    0.07
     expires
    0.07
    çİ°æľī
    0.07
    Activations Density 0.859%

    No Known Activations