© 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. 29992
    Prev
    Next
    INDEX
    Explanations

    Apache

    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
    æ§
    -0.07
    幸
    -0.07
    åľ°éĹ®éģĵ
    -0.06
    iku
    -0.06
    å¾Ĺ天
    -0.06
    eton
    -0.06
    âĢ
    -0.06
    åĪ°æĸ°
    -0.06
     haunt
    -0.06
    icher
    -0.06
    POSITIVE LOGITS
    çİīæłij
    0.09
    amac
    0.08
    åĽŀçŃĶ
    0.08
    人们çļĦçĶŁæ´»
    0.08
    波士
    0.07
    tima
    0.07
    å¦Ĥæŀľä¸Ģ个
    0.07
     usus
    0.07
    è¿Ļ个åĽŀçŃĶ
    0.07
    Originally
    0.07
    Activations Density 0.027%

    No Known Activations