© 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. 32160
    Prev
    Next
    INDEX
    Explanations

    correct or corrected reports

    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
     Rubin
    -0.07
    ratio
    -0.06
    ä¸İä½ľçĶ¨
    -0.06
    èĢĮå½ĵ
    -0.06
     Rum
    -0.06
    æĺ¯ä½ķ
    -0.06
    tak
    -0.06
     couple
    -0.06
     Planet
    -0.06
    Planet
    -0.06
    POSITIVE LOGITS
    correct
    0.08
    æŃ£ç¡®
    0.08
    éĢIJä¸Ģ
    0.08
    éĢIJ
    0.08
    _visitor
    0.07
    对åºĶ
    0.07
    对çħ§
    0.07
    éĢIJ项
    0.07
    æĽ¿æį¢
    0.07
    Correct
    0.07
    Activations Density 0.004%

    No Known Activations