© 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. 15916
    Prev
    Next
    INDEX
    Explanations

    section merely

    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
    åıĪä¸į失
    -0.08
    ÑĬÑĤ
    -0.08
     degusta
    -0.08
    ä¹İåħ¶
    -0.07
    åľ¨åĨħçļĦ
    -0.07
     sconos
    -0.07
    人以
    -0.07
    åľ¨éĩĮéĿ¢
    -0.07
    ä¸Ģ大
    -0.07
    ’d
    -0.07
    POSITIVE LOGITS
     are
    0.08
    ystems
    0.08
    uros
    0.07
     is
    0.07
     typically
    0.07
     often
    0.07
    åĴĮåľ¨
    0.06
    zor
    0.06
     always
    0.06
    ople
    0.06
    Activations Density 0.322%

    No Known Activations