© 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. 19862
    Prev
    Next
    INDEX
    Explanations

    code markers

    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
    .xhtml
    -0.09
    agin
    -0.07
    ĥģ
    -0.07
    èĴ¸èĴ¸
    -0.07
    agh
    -0.07
    è¿ĩæĿ¥
    -0.07
    å½ĵå½Ĵ
    -0.07
    åĪ
    -0.07
     afer
    -0.07
    Õ»
    -0.07
    POSITIVE LOGITS
    çłº
    0.07
    äºĮ人çļĦ
    0.07
     SECOND
    0.06
    olvers
    0.06
     Autob
    0.06
     hil
    0.06
    æĶ¹è§Ĥ
    0.06
    ylation
    0.06
    aron
    0.06
    åį¡æĭī
    0.06
    Activations Density 0.025%

    No Known Activations