© 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. 56213
    Prev
    Next
    INDEX
    Explanations

    Local Group and universe

    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
    _styles
    -0.08
     newState
    -0.08
    å¾Ģå¾Ģ
    -0.08
    imitives
    -0.08
    sene
    -0.08
    å¾Ģå¾Ģæĺ¯
    -0.07
    ãģ«ãĤĪãģ£ãģ¦ãģ¯
    -0.07
    elize
    -0.07
    arez
    -0.07
    _areas
    -0.07
    POSITIVE LOGITS
     currently
    0.08
    ä¿Ŀåį«æĪĺ
    0.08
    缮åīį
    0.07
    -sized
    0.07
    currently
    0.07
     subs
    0.07
    å¨
    0.07
     ÙĨØŃÙĨ
    0.07
    éĺ²åį«
    0.06
    太éĺ³ç³»
    0.06
    Activations Density 0.041%

    No Known Activations