© 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. 31451
    Prev
    Next
    INDEX
    Explanations

    paragraph tags

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    æľ¬å¸ĸ
    -0.10
    ermann
    -0.09
    egur
    -0.09
    ertools
    -0.09
    erman
    -0.09
    zare
    -0.09
    trup
    -0.09
    åħ¨éĥ¨è¯Ħ论
    -0.08
    änn
    -0.08
    urgeon
    -0.08
    POSITIVE LOGITS
    大æĦı
    0.07
    éĩĮçļĦ
    0.07
    matic
    0.07
    åĨħçļĦ
    0.06
    (s
    0.06
    à¹ģรà¸ģ
    0.06
     explaining
    0.06
     describing
    0.06
    0.06
    sweise
    0.06
    Activations Density 0.029%

    No Known Activations