© 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. 61928
    Prev
    Next
    INDEX
    Explanations

    symbols like `+` `\sqrt` `^` `beta`

    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
    å¸Ī大
    -0.07
    èĢĺ
    -0.07
    ×Ļ×Ļ
    -0.07
    pty
    -0.07
    æľį
    -0.06
    åĨħåĬŁ
    -0.06
     Expected
    -0.06
     lụa
    -0.06
    æĹłä»»ä½ķ
    -0.06
    /grid
    -0.06
    POSITIVE LOGITS
    æĹ¥ä»¥
    0.08
    åħ¬å¼Ģåıij
    0.08
    ä½łè¯´çļĦ
    0.07
    èĮĥåĽ´çļĦ
    0.07
    bern
    0.07
    Walk
    0.07
    æĭĽ
    0.07
    icÃŃ
    0.07
    ÃŃc
    0.07
    ób
    0.07
    Activations Density 0.001%

    No Known Activations