© 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. 30795
    Prev
    Next
    INDEX
    Explanations

    code structure or data types

    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
     co
    -0.08
    -0.07
    anne
    -0.06
    è¿Ļ个è§Ĵèī²
    -0.05
     mar
    -0.05
     bo
    -0.05
     Ama
    -0.05
     “
    -0.05
     "/",
    -0.05
    è¦ģè¿Ľè¡Į
    -0.05
    POSITIVE LOGITS
    循
    0.09
    uhe
    0.09
    issant
    0.08
    åħ¨æľ¬å°ı说
    0.08
    angkalan
    0.08
    ë´
    0.08
    upart
    0.08
    onique
    0.08
    bih
    0.08
    æľ¬å°ı说
    0.08
    Activations Density 0.005%

    No Known Activations