© 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. 46884
    Prev
    Next
    INDEX
    Explanations

    communication systems, law, manufacturing semiconductor, plumbing installations, therapeutic counselling, process operations, networks such, genetics is, entertainment,

    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
    ITER
    -0.08
     Cucina
    -0.07
    ffset
    -0.07
    ounced
    -0.07
    ãģ»
    -0.07
    ongen
    -0.06
    ç§ijéĻ¢
    -0.06
    ีà¹īย
    -0.06
    alous
    -0.06
    é²²
    -0.06
    POSITIVE LOGITS
    åŃ¦ä¹łäº¤æµģ
    0.07
    lesi
    0.07
    les
    0.07
    çłĶ究é¢ĨåŁŁ
    0.07
    inke
    0.07
     Ut
    0.07
    æĬĢæľ¯é¢ĨåŁŁ
    0.07
    å°¤åħ¶åľ¨
    0.06
    é«ĺçŃīä¸ĵç§ijåŃ¦æł¡
    0.06
    ä¸ŃæĮĩ
    0.06
    Activations Density 0.339%

    No Known Activations