© 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. 46075
    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
    noz
    -0.07
    ibur
    -0.07
     Olsen
    -0.06
    ================================================================
    -0.06
    ight
    -0.06
    éĬ·
    -0.06
    */),
    -0.06
    áĥĶáĥijáĥĺáĥĹ
    -0.06
    èĤ²
    -0.06
    езда
    -0.06
    POSITIVE LOGITS
    ÐĹÐŀ
    0.07
    纵è§Ĥ
    0.07
    isir
    0.07
    REA
    0.07
    oded
    0.07
    opan
    0.07
    WN
    0.07
    iges
    0.07
    MaxLength
    0.06
    天ä¸ĭ第ä¸Ģ
    0.06
    Activations Density 0.000%

    No Known Activations