© 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. 64809
    Prev
    Next
    INDEX
    Explanations

    rules and operations

    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
    _uploaded
    -0.08
    amedi
    -0.07
     CÃģ
    -0.07
    该产åĵģ
    -0.07
    Suppress
    -0.07
    apura
    -0.07
    ingend
    -0.07
    rauch
    -0.07
    webkit
    -0.07
    olut
    -0.07
    POSITIVE LOGITS
     allowed
    0.09
    ä»»ä½ķæŶåĢĻ
    0.09
    æ¯ı次
    0.09
    åħģ许çļĦ
    0.09
    æĵįä½ľçļĦ
    0.08
    æĵįä½ľ
    0.08
    çļĦæĵįä½ľ
    0.08
    两ç§į
    0.08
    æĶ¹åıĺ
    0.08
    çļĦä»»ä½ķ
    0.08
    Activations Density 0.029%

    No Known Activations