© 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. 61041
    Prev
    Next
    INDEX
    Explanations

    external, collaborative, other people, Hold

    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
    èĩªè¡Į
    -0.08
    èĩªä¸»
    -0.08
    äum
    -0.08
    èĩªè¡Įæī¿æĭħ
    -0.08
    XMLElement
    -0.07
    йн
    -0.07
    à¸ģาล
    -0.07
    èĩªè´¹
    -0.07
    alkan
    -0.07
    èĩªè¡ĮæıIJä¾Ľ
    -0.07
    POSITIVE LOGITS
    å¤ĸéĥ¨
    0.14
     external
    0.14
    çļĦå¤ĸéĥ¨
    0.13
    æ¯Ķèĩªå·±
    0.13
     externally
    0.12
    external
    0.12
    å¤ĸåĬĽ
    0.12
     External
    0.12
    External
    0.12
    ä¾Ŀèµĸ
    0.11
    Activations Density 0.222%

    No Known Activations