© 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. 13388
    Prev
    Next
    INDEX
    Explanations

    branch structure

    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
    åħļç»Ħ
    -0.07
    asted
    -0.07
    ä¸Ĭ好
    -0.07
     Bah
    -0.07
    _pkg
    -0.07
     bah
    -0.07
    íĺ¼
    -0.07
     upfront
    -0.06
    é¹Ń
    -0.06
    大麦
    -0.06
    POSITIVE LOGITS
     sub
    0.09
     branche
    0.08
    åĪĨæĶ¯
    0.08
    -indent
    0.08
     branch
    0.08
    oura
    0.07
    unga
    0.07
    æ·±åħ¥çłĶ究
    0.07
    äºĮ级
    0.07
    åŃIJ
    0.07
    Activations Density 0.081%

    No Known Activations