© 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. 62088
    Prev
    Next
    INDEX
    Explanations

    years written in parentheses

    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
    榻
    -0.08
    åģļäºĭæĥħ
    -0.07
    å§ĵ
    -0.07
    çĴŀ
    -0.07
    çĶ¨å®ŀéĻħè¡ĮåĬ¨
    -0.07
    æ½¢
    -0.07
    czyn
    -0.07
    _LAYOUT
    -0.06
     shed
    -0.06
    åĭĻ
    -0.06
    POSITIVE LOGITS
    æݨåĩºçļĦ
    0.08
    åıijè¡ĮçļĦ
    0.07
    æݨåĩº
    0.07
     Associations
    0.07
    åıijè¡Į
    0.07
    Association
    0.07
    APPER
    0.06
    èī³éĺ³
    0.06
    çļĦä¸Ģ款
    0.06
    代çļĦ
    0.06
    Activations Density 0.410%

    No Known Activations