© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14227
    Prev
    Next
    INDEX
    Explanations

    why

    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
     ugyanis
    -0.07
     memang
    -0.07
    æĺ¯åIJ¦ä¸İ
    -0.07
     infatti
    -0.07
    åĪĻ为
    -0.06
    ç¡®æľī
    -0.06
    uger
    -0.06
    æĺ¯åIJ¦ç¬¦åIJĪ
    -0.06
    éĢļè¿ĩä¸İ
    -0.06
    åĿĩå·²
    -0.06
    POSITIVE LOGITS
    åģıåģı
    0.11
    ãģĵãĤĵãģªãģ«
    0.11
     à¸Ĺำà¹Ħม
    0.10
     begitu
    0.10
    为ä»Ģä¹Ī
    0.10
    è¿Ļä¹Īå¿«
    0.10
    è¿Ļä¹Īå¤ļ人
    0.10
    ãĤıãģĸãĤıãģĸ
    0.10
     bother
    0.10
    åį´ä¸įèĥ½
    0.09
    Activations Density 0.173%

    No Known Activations