© 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. 1748
    Prev
    Next
    INDEX
    Explanations

    datesortechnicalterms

    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
    )|(
    -0.07
     prop
    -0.07
    .opt
    -0.06
    기íķľ
    -0.06
     ident
    -0.06
    endra
    -0.06
    ç²īåĪº
    -0.06
     optim
    -0.06
     billed
    -0.06
    åĴĮæľĢ
    -0.06
    POSITIVE LOGITS
    hode
    0.08
    Dos
    0.08
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    0.08
     chÄĥng
    0.07
    রà§ĩ
    0.07
     dijer
    0.07
    arkan
    0.07
    agic
    0.07
    饥
    0.07
    èĩªè¨Ģ
    0.07
    Activations Density 0.284%

    No Known Activations