© 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. 29390
    Prev
    Next
    INDEX
    Explanations

    data type declarations

    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
    mos
    -0.08
    ä¸į足çļĦ
    -0.07
    森æŀĹåħ¬åĽŃ
    -0.07
    ä»Ĭå¹´ä¸ĬåįĬå¹´
    -0.07
    trit
    -0.07
    æĹłä¸į
    -0.07
    åĭĩäºİ
    -0.07
     Lemb
    -0.07
    som
    -0.07
    remos
    -0.07
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.08
    ä¸Ģç³»åĪĹçļĦ
    0.08
    ä¸Ģç³»åĪĹ
    0.07
    &action
    0.07
    èĬĿ
    0.06
    åį¡è¥¿
    0.06
     olyan
    0.06
    าà¸Ĭ
    0.06
    åºĶå½ĵæĮīçħ§
    0.06
    agic
    0.06
    Activations Density 0.004%

    No Known Activations