© 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. 57361
    Prev
    Next
    INDEX
    Explanations

    systems, services, and media

    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
    åľ¨åħ·ä½ĵ
    -0.08
    çĻ¾åĪĨä¹ĭçĻ¾
    -0.08
    comings
    -0.08
    ortable
    -0.07
    åľ¨å®ŀéĻħ
    -0.07
    tures
    -0.07
    ×ķ×ļ
    -0.07
    ÙĬص
    -0.07
     specifier
    -0.07
    åħ¨éĥ¨è´£ä»»
    -0.07
    POSITIVE LOGITS
    为社ä¼ļ
    0.07
    积æŀģåIJijä¸ĬçļĦ
    0.07
    reau
    0.07
    ora
    0.07
    åĴĮæķĻèĤ²
    0.07
    mar
    0.07
     genie
    0.06
    ai
    0.06
     дÑĥÑħов
    0.06
     pir
    0.06
    Activations Density 0.135%

    No Known Activations