© 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. 48528
    Prev
    Next
    INDEX
    Explanations

    consumed or lost

    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
    çĭ¬
    -0.07
    square
    -0.07
    ullo
    -0.07
    üs
    -0.06
     inherited
    -0.06
    å¯¹çĽ¸åħ³
    -0.06
    综åIJĪæĶ¹éĿ©
    -0.06
     built
    -0.06
    env
    -0.06
    缸åħ³ä¸ĵä¸ļ
    -0.06
    POSITIVE LOGITS
    ducted
    0.09
    äºĨå¤ļå°ij
    0.09
    åĴĮ被
    0.09
    æİīçļĦ
    0.08
     amounts
    0.08
     portion
    0.08
    rowned
    0.08
    ä¸ŃéĢĶ
    0.08
     ë§Įíģ¼
    0.07
    CASCADE
    0.07
    Activations Density 0.008%

    No Known Activations