© 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. 28789
    Prev
    Next
    INDEX
    Explanations

    dominant prevalence

    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
    æīĢ为
    -0.08
    æľĢç®Ģåįķ
    -0.08
    æľĢç®ĢåįķçļĦ
    -0.07
    éĢĤåºĶèĥ½åĬĽ
    -0.07
    szer
    -0.07
    ÑģÑĤÑĢÑı
    -0.07
    å¾Īç®Ģåįķ
    -0.07
    naz
    -0.07
    顺åĪ©éĢļè¿ĩ
    -0.07
    pearance
    -0.07
    POSITIVE LOGITS
     dominance
    0.16
    ä¸»å¯¼åľ°ä½į
    0.15
     dominant
    0.14
    主导
    0.13
     Domin
    0.13
     prominence
    0.13
     dominating
    0.13
    Domin
    0.12
    åįłæ¯Ķ
    0.12
     domin
    0.12
    Activations Density 0.082%

    No Known Activations