© 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. 22865
    Prev
    Next
    INDEX
    Explanations

    stick with, or I

    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
    æł¹æľ¬æ²¡æľī
    -0.08
    arl
    -0.07
    èĢĮæĪij们
    -0.07
    æł¹æľ¬æ²¡
    -0.07
    çŁ¥éģĵåIJĹ
    -0.07
    éĥijéĩį声æĺİ
    -0.07
    åŀĴ
    -0.07
    èµĸ
    -0.06
     acab
    -0.06
    æĽ´åĪ«è¯´
    -0.06
    POSITIVE LOGITS
     myself
    0.10
    çIJĨçĶ±æĺ¯
    0.08
    è¿Ļæĺ¯æĪijçļĦ
    0.07
    awang
    0.07
     cautiously
    0.07
    并å°Ĩåħ¶
    0.07
    æĹ¢çĦ¶æĺ¯
    0.07
    маÑĤа
    0.07
    ä¸į妥
    0.07
    è¯ķè¯ķçľĭ
    0.07
    Activations Density 0.007%

    No Known Activations