© 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. 1950
    Prev
    Next
    INDEX
    Explanations

    political parties and countries

    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
     поблизоÑģÑĤи
    -0.07
    æľīä¸ĭåĪĹ
    -0.07
    ä¿ĥ使
    -0.07
    ofer
    -0.07
    <typeof
    -0.06
    omer
    -0.06
    ÐĺÐij
    -0.06
    åĴĮåľ¨
    -0.06
    éĵ¡
    -0.06
    SourceType
    -0.06
    POSITIVE LOGITS
    æķ´ä½ĵçļĦ
    0.09
    åİĨåı²ä¸Ĭ
    0.09
    èµĸ以
    0.09
    æķ´ä½ĵ
    0.08
    -wide
    0.08
    åºĶæľīçļĦ
    0.08
    åıijå±ķæĸ¹åIJij
    0.08
    æķ´é«Ķ
    0.08
    åİĨåı²ä¸ĬçļĦ
    0.08
    äºŁ
    0.07
    Activations Density 0.500%

    No Known Activations