© 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. 41163
    Prev
    Next
    INDEX
    Explanations

    platform

    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
    Ĺ
    -0.08
    PerPage
    -0.07
    eland
    -0.07
    สà¸Ļิà¸Ĺ
    -0.07
    代表大ä¼ļ
    -0.07
    åĽ¢éĺŁåIJĪä½ľç²¾ç¥ŀ
    -0.07
    ftime
    -0.07
    aline
    -0.06
    immer
    -0.06
    ayah
    -0.06
    POSITIVE LOGITS
    oenix
    0.09
    armor
    0.08
    ional
    0.08
    matic
    0.08
    unjuk
    0.08
    积çĶµ
    0.08
    ewise
    0.08
    unky
    0.08
    åĴĮåĨħ容
    0.08
    建设ä¸İ
    0.08
    Activations Density 0.040%

    No Known Activations