© 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. 24705
    Prev
    Next
    INDEX
    Explanations

    listing numbers 3, 5, 6, 8

    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
    ickle
    -0.07
    ARES
    -0.07
    ä¸Ĭ好
    -0.07
    åĴĮæľĢ
    -0.06
     Sawyer
    -0.06
    åĪ°å¤´
    -0.06
     tor
    -0.06
     머
    -0.06
    è¾ĸ
    -0.06
    iany
    -0.06
    POSITIVE LOGITS
    èĢĮä¸į
    0.09
    è·³è¿ĩ
    0.08
    èĢĮéĿŀ
    0.08
    instead
    0.08
    èĢĮä¸įæĺ¯
    0.07
    .sparse
    0.07
    rather
    0.07
    éĹ´éļĻ
    0.07
     instead
    0.07
    anse
    0.07
    Activations Density 0.055%

    No Known Activations