© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2872
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis or punctuation

    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
     ann
    -0.07
    款
    -0.06
     poste
    -0.06
     Gat
    -0.06
    Ø°
    -0.06
    ä¸įè¦ģ太
    -0.06
    带çĬ¶
    -0.06
     Duffy
    -0.06
     try
    -0.06
    éģĵè¿ľ
    -0.06
    POSITIVE LOGITS
     terc
    0.08
    uggle
    0.08
    quals
    0.08
     enthus
    0.07
    wm
    0.07
    è¿Ļæĸ¹éĿ¢
    0.07
    .mov
    0.07
    é¦Ħ
    0.07
    erge
    0.07
    initely
    0.07
    Activations Density 0.333%

    No Known Activations