© 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. 11942
    Prev
    Next
    INDEX
    Explanations

    following "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
    enet
    -0.08
    .exports
    -0.08
    mlink
    -0.07
     kurv
    -0.07
    enn
    -0.07
    Destroyed
    -0.07
    æĸ°éĹ»ç½ij
    -0.07
    åĩºåİ»çļĦ
    -0.07
    åĩºçļĦ
    -0.07
    emy
    -0.07
    POSITIVE LOGITS
    åºĶçĶ¨äºİ
    0.08
    åºĶçĶ¨åĪ°
    0.07
    è¿IJçĶ¨äºİ
    0.07
    è¿IJçĶ¨åĪ°
    0.07
    代åħ¥
    0.07
    éĢĤçĶ¨äºİ
    0.06
    éĴĪ对
    0.06
     Applied
    0.06
    设å®ļ
    0.06
     Walters
    0.06
    Activations Density 0.018%

    No Known Activations