© 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. 29198
    Prev
    Next
    INDEX
    Explanations

    question, underlying, hidden, option, motivated

    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
    .codes
    -0.08
    vice
    -0.08
    åıĬåħ¶åºĶçĶ¨
    -0.07
    åıįèĢĮ
    -0.07
    æĻĤåĢĻ
    -0.07
    ä¸İåIJ¦
    -0.07
     ÄĤ
    -0.07
    æ³¢å°Ķ
    -0.07
    åħ³éĶ®æĺ¯
    -0.07
    缸åħ³åĨħ容
    -0.07
    POSITIVE LOGITS
    ble
    0.07
    astle
    0.07
    é¾ĻåŁİ
    0.06
    ä¼ģ
    0.06
    eggia
    0.06
    èĵĦ
    0.06
    çļĦæĦıæĢĿæĺ¯
    0.06
    LY
    0.06
    æĭħå¿ĥ
    0.06
    uble
    0.06
    Activations Density 0.003%

    No Known Activations