© 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. 3868
    Prev
    Next
    INDEX
    Explanations

    email sign-offs

    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
     <![
    -0.08
    ç»ĿæĹł
    -0.07
    usting
    -0.07
    èĪ
    -0.07
    eki
    -0.07
    immer
    -0.07
     stimm
    -0.06
    à¸Ńà¸ģ
    -0.06
    èī¯ä¹ħ
    -0.06
    hell
    -0.06
    POSITIVE LOGITS
    æİĮä¸Ĭ
    0.08
    çĻ¾äºĭ
    0.07
    ardan
    0.07
    код
    0.07
    ä¿¡æģ¯æĿ¥æºIJ
    0.07
    éĿĴäºij
    0.07
    åı²ä¸ĬæľĢ
    0.07
    ogos
    0.07
    å¢Ĵ
    0.07
    wort
    0.06
    Activations Density 0.120%

    No Known Activations