© 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. 39038
    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
    _Top
    -0.08
    ÏģαÏĥ
    -0.07
    agger
    -0.07
    åIJĥä¸ĢäºĽ
    -0.07
    åľ°äºĨ解
    -0.07
    abella
    -0.07
    æĺ¯ä¸Ģåıª
    -0.07
    ese
    -0.07
    _DT
    -0.07
    æĺ¯ä¸Ģæľ¬
    -0.07
    POSITIVE LOGITS
    uire
    0.06
    odal
    0.06
    wald
    0.06
    åIJį为
    0.06
    vik
    0.06
    izzard
    0.06
    à´±
    0.06
     De
    0.06
    à¹Ģà¸Ķ
    0.06
    ظاÙĩر
    0.06
    Activations Density 0.000%

    No Known Activations