© 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. 48890
    Prev
    Next
    INDEX
    Explanations

    text after punctuation

    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
    åįĩåĪĿ
    -0.08
    å¨Ĩ
    -0.08
    azon
    -0.07
    åĪĨéĴŁåīį
    -0.07
    .flat
    -0.07
    ogs
    -0.07
    ÐĹе
    -0.07
    énom
    -0.07
    ereg
    -0.07
    ibun
    -0.07
    POSITIVE LOGITS
    并举
    0.09
    åºĶçĶ¨åĪ°
    0.08
    举个ä¾ĭåŃIJ
    0.08
    ä¾ĭå¦Ĥ
    0.07
    举ä¾ĭ
    0.07
    è°¬
    0.07
    æĭŃ缮
    0.07
    åºĶçĶ¨åľ¨
    0.07
     definition
    0.07
    /examples
    0.07
    Activations Density 0.315%

    No Known Activations