© 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. 7475
    Prev
    Next
    INDEX
    Explanations

    Ambuja Cement Limited

    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
    以åıĬä¸ĢäºĽ
    -0.07
    '](
    -0.07
     ê´Ģ볨íķĺìŬ
    -0.06
    ardu
    -0.06
    /{}/
    -0.06
    "":
    -0.06
    æĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.06
    ”—
    -0.06
    èĻ½çĦ¶æ²¡æľī
    -0.06
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.07
    	  ↵
    0.07
    åĪ©çī©
    0.07
    ä¸Ĭä¼łèĢħ
    0.07
    ãĤīãģĻ
    0.06
    ierend
    0.06
    客
    0.06
     âĸ·
    0.06
    ↵			↵
    0.06
    éºĵ
    0.06
    Activations Density 0.113%

    No Known Activations