© 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. 2552
    Prev
    Next
    INDEX
    Explanations

    producer, manager, oversee

    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
    pector
    -0.08
    诸å¦Ĥ
    -0.08
    aup
    -0.08
    spb
    -0.07
    æĸ°æ°Ķ象
    -0.07
    uf
    -0.07
    vik
    -0.07
    ếch
    -0.07
     Wouldn
    -0.07
    ael
    -0.07
    POSITIVE LOGITS
    çĶ¨äºİ
    0.08
    è¿Ļæĺ¯å¯¹
    0.08
    æĺ¯çĶ¨æĿ¥
    0.08
    çĶ¨æĿ¥
    0.07
    à¹ĥà¸Ĭà¹īà¹ĥà¸Ļà¸ģาร
    0.07
    主è¦ģçĶ¨äºİ
    0.07
    以身
    0.07
    è´Łè´£å¯¹
    0.07
    çĶ¨ä»¥
    0.07
     Ens
    0.07
    Activations Density 0.024%

    No Known Activations