© 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. 26390
    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
    obs
    -0.07
    IMER
    -0.07
    马èĻİ
    -0.06
    第ä¸Ģ代
    -0.06
    elmi
    -0.06
    è§Ħ模çļĦ
    -0.06
    æĹıçļĦ
    -0.06
    å¯Ĩæĸ¯
    -0.06
    éĩĩçĶ¨çļĦæĺ¯
    -0.06
    opoulos
    -0.06
    POSITIVE LOGITS
    æĥ³ä¸įåĪ°
    0.07
    usse
    0.07
    åĶĩ
    0.07
     Preg
    0.07
    oman
    0.07
    FunctionFlags
    0.07
    fab
    0.07
    交æīĢ
    0.07
     depor
    0.07
    工大
    0.07
    Activations Density 0.000%

    No Known Activations