© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48189
    Prev
    Next
    INDEX
    Explanations

    Nobel Prize awarded

    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
    æĭŁå»º
    -0.07
    itsu
    -0.07
    梨
    -0.07
    éĽĨåħ¨
    -0.07
     preg
    -0.07
     ÑĢедакÑĨии
    -0.07
     kÃŃs
    -0.07
     NotImplemented
    -0.07
    åıijå¸ĥæĹ¥æľŁ
    -0.06
     Followers
    -0.06
    POSITIVE LOGITS
     Nobel
    0.15
     deserved
    0.10
     awarded
    0.10
    èİ·
    0.10
    èİ·å¥ĸ
    0.09
    诺è´Ŀå°Ķ
    0.09
     ÑĥдоÑģÑĤо
    0.09
     award
    0.09
    èį£èİ·
    0.09
     Premio
    0.09
    Activations Density 0.210%

    No Known Activations