© 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. 26245
    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
    è¶ģ
    -0.07
    çons
    -0.07
    pite
    -0.07
    å·®ä¸į
    -0.06
     Cle
    -0.06
    _languages
    -0.06
    etwork
    -0.06
    çļĦéĢĶå¾Ħ
    -0.06
    ä¸ĢçĽ´æ²¡
    -0.06
    à¯įà®ļ
    -0.06
    POSITIVE LOGITS
    aku
    0.10
    anut
    0.09
    adura
    0.09
    à¹Ģà¸Ľà¸¥
    0.08
    NaN
    0.08
    ä¸įæķ£
    0.08
    alue
    0.08
    лиÑĤ
    0.07
    agna
    0.07
    igas
    0.07
    Activations Density 0.000%

    No Known Activations