© 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. 45727
    Prev
    Next
    INDEX
    Explanations

    hydrocarbon compounds

    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
     нез
    -0.07
     setup
    -0.06
     Gel
    -0.06
    Salt
    -0.06
    åĶ¯ä¸Ģ
    -0.06
    æľªå±¥è¡Į
    -0.06
    çļĦåĶ¯ä¸Ģ
    -0.06
    åıĮèĦļ
    -0.06
    éļIJæĢ§
    -0.06
    æĹłéĺ»
    -0.06
    POSITIVE LOGITS
     fragmentation
    0.10
    ä¸īäºĶ
    0.09
    processable
    0.09
    ysize
    0.09
    -rich
    0.09
    heu
    0.08
    fragment
    0.08
     sey
    0.08
     conglomer
    0.08
    åIJĦæĹı
    0.08
    Activations Density 0.040%

    No Known Activations