© 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. 18493
    Prev
    Next
    INDEX
    Explanations

    optimising

    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
    æµ·åĨħå¤ĸ
    -0.07
    éªĮèµĦ
    -0.07
    Convertible
    -0.06
    orz
    -0.06
    akra
    -0.06
     ED
    -0.06
    ^n
    -0.06
    enaus
    -0.06
    andle
    -0.06
    åıĪä¸įæĺ¯
    -0.06
    POSITIVE LOGITS
    ãģªãģĹ
    0.08
    ä¼łç»ŁçļĦ
    0.08
    æĪij们认为
    0.08
    traditional
    0.08
    ä¼łç»Ł
    0.07
    对çħ§ç»Ħ
    0.07
     differed
    0.07
     traditional
    0.07
     versus
    0.07
    _vs
    0.07
    Activations Density 1.763%

    No Known Activations