© 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. 2615
    Prev
    Next
    INDEX
    Explanations

    programmatic variables and code snippets

    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
    离ä¸įå¼Ģ
    -0.08
    ª
    -0.08
    èĢģè¡Ĺ
    -0.07
     rew
    -0.07
    ä¸įæĶ¹
    -0.07
    为äºĨ解åĨ³
    -0.07
    Ùħا
    -0.07
    éĥ½ç¦»ä¸įå¼Ģ
    -0.07
    åįķä¸ĢçļĦ
    -0.07
    intai
    -0.06
    POSITIVE LOGITS
     empty
    0.12
    empty
    0.12
    Empty
    0.12
    çļĦ空
    0.11
     Empty
    0.11
    空
    0.11
    空çļĦ
    0.11
     Attempt
    0.11
     пÑĥÑģÑĤ
    0.11
    为空
    0.10
    Activations Density 0.397%

    No Known Activations