© 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. 30117
    Prev
    Next
    INDEX
    Explanations

    extrapolate continue trends rate

    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
    å§ĵ
    -0.08
    ä¸Ģåij³
    -0.07
    ä¸ĢæĬĬæīĭ
    -0.07
    ä¸Ģ身
    -0.07
    åĪ¶åº¦åĴĮ
    -0.06
    ä¸Ģä½į
    -0.06
    为æ°ij
    -0.06
    ä¸Ģä¾ĭ
    -0.06
    Õ»
    -0.06
     Robbins
    -0.06
    POSITIVE LOGITS
     traced
    0.09
     extrapol
    0.08
    ç½
    0.08
     backward
    0.08
    Patr
    0.08
    imony
    0.08
     tracing
    0.08
    lox
    0.08
     continuation
    0.08
     penc
    0.08
    Activations Density 0.001%

    No Known Activations