© 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. 38577
    Prev
    Next
    INDEX
    Explanations

    before

    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
    çĤİçĤİ
    -0.07
    åĪ¶åº¦æĶ¹éĿ©
    -0.07
    æ¾İæ¹ĥ
    -0.07
    adero
    -0.07
    obb
    -0.07
    _REV
    -0.07
     NotImplementedError
    -0.06
    edReader
    -0.06
    pic
    -0.06
    é¢Į
    -0.06
    POSITIVE LOGITS
     preceding
    0.12
    preced
    0.10
     before
    0.10
     antes
    0.10
    -before
    0.10
    åīįç½®
    0.09
    before
    0.09
    _before
    0.09
    åľ¨æѤä¹ĭåīį
    0.09
     preced
    0.09
    Activations Density 0.105%

    No Known Activations