© 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. 62662
    Prev
    Next
    INDEX
    Explanations

    .prototype conversion

    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
    åıĪæĬĬ
    -0.08
    éĿĵ
    -0.08
    anya
    -0.08
    å·²ç»ıæĬĬ
    -0.07
    åĦ²
    -0.07
    Forg
    -0.07
    æĬĬä½łçļĦ
    -0.07
    æĬĬæĪijçļĦ
    -0.07
    uki
    -0.07
    à§ģà¦ķ
    -0.07
    POSITIVE LOGITS
    еÑĢа
    0.07
    è¿Ľè¡Įå¤ĦçIJĨ
    0.07
    .ribbon
    0.07
    å¤ĸäºĭ
    0.07
    çĸ¾
    0.07
    sse
    0.07
    owitz
    0.06
    èĥ½è¢«
    0.06
     transformation
    0.06
     destined
    0.06
    Activations Density 0.356%

    No Known Activations