© 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. 56691
    Prev
    Next
    INDEX
    Explanations

    choice or option

    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
     dépass
    -0.07
    sud
    -0.06
     Auxiliary
    -0.06
    REATE
    -0.06
    åıĹåĪ°å½±åĵį
    -0.06
    è¶ħè¶Ĭ
    -0.06
     Quite
    -0.06
    reu
    -0.06
    è´Łè´£åIJĮå¿Ĺ
    -0.06
     madrugada
    -0.06
    POSITIVE LOGITS
     potentially
    0.09
    instead
    0.08
    æĽ´ç¬¦åIJĪ
    0.08
    better
    0.08
     instead
    0.08
    继ç»Ńä¿ĿæĮģ
    0.08
     Option
    0.08
    æľīæĽ´å¥½çļĦ
    0.08
    好åij¢
    0.08
     вмеÑģÑĤо
    0.07
    Activations Density 0.166%

    No Known Activations