© 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. 56148
    Prev
    Next
    INDEX
    Explanations

    foods, fats, sugars, caffeine, sodium, alcohol

    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
    å¼¥
    -0.08
    å½Į
    -0.07
     Pew
    -0.07
     Millenn
    -0.07
    disp
    -0.07
    æĹłéĹ»
    -0.07
    èĩĤ
    -0.07
    allee
    -0.07
    gil
    -0.07
     Disp
    -0.07
    POSITIVE LOGITS
    å¯ĮåIJ«
    0.10
    åIJ«æľī
    0.10
    å¿Į
    0.10
    åĪºæ¿ĢæĢ§é£Łçī©
    0.09
     foods
    0.09
    çĶŁåĨ·
    0.09
    软
    0.08
    åĪ¶åĵģ
    0.08
    æ¸ħæ·¡
    0.08
    åIJ«
    0.08
    Activations Density 0.035%

    No Known Activations