© 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. 43254
    Prev
    Next
    INDEX
    Explanations

    Chinese and English mixed phrases

    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
    <?>>
    -0.08
    hiri
    -0.08
    watan
    -0.07
    åıªè¦ģä½ł
    -0.07
    idon
    -0.07
    ensee
    -0.07
     whichever
    -0.07
    Ñħо
    -0.07
    ãģĵãģ¨ãģ§ãģĻ
    -0.07
     zwar
    -0.07
    POSITIVE LOGITS
    æľīåĵªäºĽ
    0.16
    è¿ĺæľīåĵªäºĽ
    0.15
    æĺ¯å¦Ĥä½ķ
    0.15
    åºĶ该å¦Ĥä½ķ
    0.14
    å¦Ĥä½ķæīįèĥ½
    0.13
    éĥ½æľīåĵªäºĽ
    0.13
    æĺ¯æĢİæł·
    0.13
    åĵªäºĽ
    0.13
    æľīåĵª
    0.13
    该å¦Ĥä½ķ
    0.13
    Activations Density 0.034%

    No Known Activations