© 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. 20626
    Prev
    Next
    INDEX
    Explanations

    academic contexts and entities

    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
    olf
    -0.08
    ACING
    -0.08
    aco
    -0.08
    ê´Ħ
    -0.08
    ãĤĥ
    -0.08
    ä¾łä¼ł
    -0.08
    ERRU
    -0.07
    orsch
    -0.07
    ણ
    -0.07
    à¸Ħà¹Į
    -0.07
    POSITIVE LOGITS
    çķĮçļĦ
    0.09
    ä¸İå®ŀè·µ
    0.08
    人士
    0.07
    ély
    0.07
    ifice
    0.07
    çĶ¨ä¹¦
    0.07
    itative
    0.07
    åľ°ä½į
    0.07
    ès
    0.07
    åĴĮ产ä¸ļ
    0.07
    Activations Density 0.027%

    No Known Activations