© 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. 42427
    Prev
    Next
    INDEX
    Explanations

    basis and bases

    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
     yür
    -0.08
    éĺ»éļĶ
    -0.07
    第ä¸īèĢħ
    -0.07
    éĤ£éģĵ
    -0.07
    åı¸
    -0.07
    conte
    -0.07
     pandem
    -0.07
    买个
    -0.07
     Bev
    -0.07
    nalis
    -0.07
    POSITIVE LOGITS
    ä¸Ģç»Ħ
    0.08
    èĬ½
    0.07
     набоÑĢ
    0.07
    ä¸Ģå¥Ĺ
    0.07
    .arr
    0.07
    ç»ĦæĪIJçļĦ
    0.07
    .toArray
    0.07
    stash
    0.07
    ç»ĦæĪIJäºĨ
    0.07
     consisting
    0.07
    Activations Density 0.011%

    No Known Activations