© 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. 3056
    Prev
    Next
    INDEX
    Explanations

    impairment, piercing, milk-fed, baggage, wish

    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
    æľ´å®ŀ
    -0.08
    å¹³æĿ¿
    -0.08
     Plain
    -0.08
    庸
    -0.07
    å¹³åİŁ
    -0.07
    ç²Ĺ
    -0.07
    çŃĴ
    -0.07
    Plain
    -0.07
     crude
    -0.07
     Emp
    -0.07
    POSITIVE LOGITS
    åĩĮ空
    0.07
    ologne
    0.07
     intrinsic
    0.07
     голо
    0.07
     infinite
    0.07
    croft
    0.07
    èĤ¡ä»½çļĦ
    0.07
    icast
    0.07
    ìŀ
    0.07
    饥饿
    0.07
    Activations Density 0.136%

    No Known Activations