© 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. 30455
    Prev
    Next
    INDEX
    Explanations

    notable persons or things

    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
    éļIJéļIJ
    -0.08
    ä¸ºæľŁ
    -0.07
    éľĢè¦ģçļĦ
    -0.07
     hypo
    -0.07
    åºĶ该å¦Ĥä½ķ
    -0.06
    æīĢéľĢçļĦ
    -0.06
    羡
    -0.06
    é¢ĦæľŁçļĦ
    -0.06
    å°ĨæĿ¥çļĦ
    -0.06
    çħİ
    -0.06
    POSITIVE LOGITS
     notable
    0.15
     famous
    0.10
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.10
     noteworthy
    0.10
    èijĹåIJįçļĦ
    0.10
    æľĢèijĹåIJįçļĦ
    0.10
     influential
    0.10
    çŁ¥åIJįçļĦ
    0.09
    é¡¹çĽ®åIJį称
    0.09
    èijĹåIJį
    0.09
    Activations Density 0.407%

    No Known Activations