© 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. 58013
    Prev
    Next
    INDEX
    Explanations

    numeric index followed by comma

    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
    atil
    -0.08
    inom
    -0.07
    è¿Ļä¸ī
    -0.07
    åħ®
    -0.06
     Cum
    -0.06
    è¿Ļä¸ī个
    -0.06
    å®Įä¹ĭåIJİ
    -0.06
    çIJĨäºĭéķ¿
    -0.06
    å¾·åŁº
    -0.06
    æī©å±ķèµĦæĸĻ
    -0.06
    POSITIVE LOGITS
    两ä¸į误
    0.08
    è©«
    0.07
     dici
    0.07
    uç
    0.07
    å®ķ
    0.07
    åIJ©
    0.07
    uhe
    0.07
    ogl
    0.06
    åĬĽåĴĮ
    0.06
     getClass
    0.06
    Activations Density 0.041%

    No Known Activations