© 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. 16916
    Prev
    Next
    INDEX
    Explanations

    update

    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
     Join
    -0.08
    éļıçĿĢå¹´é¾ĦçļĦå¢ŀéķ¿
    -0.07
    å®īæģ¯
    -0.07
    Join
    -0.07
    join
    -0.07
    åİŁäº§åľ°
    -0.07
    .enum
    -0.07
    aternity
    -0.07
     frit
    -0.07
     Laud
    -0.07
    POSITIVE LOGITS
    æĽ´æĸ°
    0.09
    -update
    0.09
     update
    0.08
    åīįåĽŀ
    0.08
    ä¸Ĭä¸Ģ次
    0.08
    æľĢæĸ°
    0.08
     updating
    0.07
    åıĸå¾Ĺæĸ°
    0.07
    æĽ´æĸ°çļĦ
    0.07
     Update
    0.07
    Activations Density 0.005%

    No Known Activations