© 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. 23573
    Prev
    Next
    INDEX
    Explanations

    words

    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
    éĴŀ
    -0.09
    ién
    -0.08
     ditem
    -0.07
    æĢĢä¸Ń
    -0.07
    æĵįä½ľä¸Ĭ
    -0.07
    emment
    -0.07
    raphics
    -0.07
    è¿ijçļĦ
    -0.07
    eterminate
    -0.07
    表çı¾
    -0.07
    POSITIVE LOGITS
    -word
    0.09
    (words
    0.08
    æݨæķ²
    0.08
    åįķè¯į
    0.08
    Words
    0.08
     nouns
    0.07
    è¯įè¯Ń
    0.07
     words
    0.07
    çµ®
    0.07
    words
    0.07
    Activations Density 0.067%

    No Known Activations