© 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. 23627
    Prev
    Next
    INDEX
    Explanations

    raising ladder

    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
    өн
    -0.07
    å®Įæķ´åľ°
    -0.07
    æĬ¥è®¯
    -0.07
    åİĨåı²ä¿¡æģ¯
    -0.07
    æ¾ľ
    -0.07
    uts
    -0.07
    äºĶæĹ¥
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    bons
    -0.07
    å®Įæķ´çļĦ
    -0.06
    POSITIVE LOGITS
    -progress
    0.07
    olim
    0.07
     recol
    0.07
     AHL
    0.07
     acos
    0.07
    pira
    0.07
     Nolan
    0.07
    æļ®
    0.07
    .maximum
    0.07
    çİī溪
    0.07
    Activations Density 0.002%

    No Known Activations