© 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. 7572
    Prev
    Next
    INDEX
    Explanations

    law, warrant, merit, deserving

    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
    åĿļæĮģæĬĬ
    -0.08
    ownie
    -0.07
    sse
    -0.07
    åħĭåħ°
    -0.07
    羣æŃ£åģļåĪ°
    -0.07
    ê´ij
    -0.07
     Conse
    -0.07
    éĿĴå·ŀ
    -0.07
     Ata
    -0.07
     Willis
    -0.07
    POSITIVE LOGITS
     warrant
    0.08
    æĹ¢çĦ¶
    0.08
     merits
    0.08
    çIJĨåºĶ
    0.08
     deserving
    0.08
    åºĶäºĪ
    0.08
     warrants
    0.08
    æĹ¢çĦ¶æĺ¯
    0.08
     merit
    0.07
    undy
    0.07
    Activations Density 0.043%

    No Known Activations