© 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. 28796
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    NullOrEmpty
    -0.07
    itto
    -0.07
    خطر
    -0.07
    omini
    -0.07
    ihad
    -0.07
    横
    -0.07
    alie
    -0.06
    Ùħج
    -0.06
    æ³
    -0.06
    wyn
    -0.06
    POSITIVE LOGITS
    å¼ĺ
    0.07
    éĢĤ
    0.07
    ä¸į失
    0.07
    alex
    0.07
    Preferences
    0.06
    erias
    0.06
    ãĤ·ãĥ£ãĥ³ãĥĹ
    0.06
     sacerd
    0.06
    ä¸Ĭä¹ĺ
    0.06
    éģ©
    0.06
    Activations Density 0.000%

    No Known Activations