© 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. 30472
    Prev
    Next
    INDEX
    Explanations

    groceries, workers, languages, series, logs, temporary

    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
    çĽĬ
    -0.07
    æĪij赶紧
    -0.07
    stwo
    -0.07
    æĴµ
    -0.07
    çĥŃéŨæIJľç´¢
    -0.07
    اÙĨØ©
    -0.06
    resh
    -0.06
    azer
    -0.06
    stw
    -0.06
     cues
    -0.06
    POSITIVE LOGITS
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.10
    åľ¨æŁIJ
    0.09
     wholly
    0.08
    åīį款
    0.08
     merely
    0.08
    ìĸ´ëĤĺ
    0.08
    æĪĸåħ¶ä»ĸ
    0.08
     expressly
    0.08
    æľªåıĸå¾Ĺ
    0.08
    çĶ±è¢«åijĬ
    0.08
    Activations Density 0.114%

    No Known Activations