© 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. 60299
    Prev
    Next
    INDEX
    Explanations

    eyes of / delight of / fascination of

    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
    dings
    -0.09
    ä¸ŃåĽ½åľ¨
    -0.08
    éģ¸æīĭãģ®
    -0.08
    åħĪçĶŁçļĦ
    -0.07
    主人åħ¬
    -0.07
    ussin
    -0.07
    ä¸Ģ个人çļĦ
    -0.07
    对人çļĦ
    -0.07
    å«ĮçĬ¯
    -0.07
    æł¹æį®åĽ½å®¶
    -0.07
    POSITIVE LOGITS
    åľĪåĨħ
    0.08
    åħ«æĸ¹
    0.08
    æĹģè§Ĥ
    0.08
    çŀ©çĽ®
    0.08
    aisse
    0.08
    æĹģ人
    0.07
    廣大
    0.07
    å²Ľ
    0.07
     interna
    0.07
    ake
    0.07
    Activations Density 0.793%

    No Known Activations