© 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. 37961
    Prev
    Next
    INDEX
    Explanations

    graph api explorer

    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
    Ế
    -0.09
    )&&(
    -0.08
    å°±åľ¨è¿ĻæŶ
    -0.08
    /respond
    -0.07
    æĹ¢çĦ¶å¦ĤæѤ
    -0.07
     Ñģобой
    -0.07
    åĽłä¸ºå¥¹
    -0.07
    åľ¨ä»ĸçľĭæĿ¥
    -0.07
    hora
    -0.07
    )&&
    -0.07
    POSITIVE LOGITS
     there
    0.12
     ÙģØ¥ÙĨ
    0.09
     terdapat
    0.09
    there
    0.08
     inilah
    0.08
     sekalipun
    0.07
     it
    0.07
     we
    0.07
    unker
    0.07
    ,it
    0.07
    Activations Density 0.307%

    No Known Activations