© 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. 27289
    Prev
    Next
    INDEX
    Explanations

    using this

    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
    éb
    -0.08
    çļĦåģļæ³ķ
    -0.08
    egie
    -0.08
    ideo
    -0.07
    Contrib
    -0.07
    åIJįåĪĹåīįèĮħ
    -0.07
    该项
    -0.07
    achable
    -0.07
    å¼ĢéĶģ
    -0.07
     thắt
    -0.07
    POSITIVE LOGITS
    ux
    0.07
    åIJĪåIJĮå±¥è¡Į
    0.07
    íĭĢ
    0.07
    éron
    0.07
     inilah
    0.07
    åŁºç¡Ģä¸Ĭ
    0.06
     alone
    0.06
     ordering
    0.06
    ós
    0.06
    ä¹ĭä¸Ĭ
    0.06
    Activations Density 0.117%

    No Known Activations