© 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. 23339
    Prev
    Next
    INDEX
    Explanations

    numbers followed by operators or parentheses

    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
    .proxy
    -0.07
     traff
    -0.07
    å¿Į讳
    -0.07
    å®ŀåIJį
    -0.06
    iasi
    -0.06
    beit
    -0.06
    IMS
    -0.06
    иÑĤелÑĮно
    -0.06
    éĩİ
    -0.06
    ovo
    -0.06
    POSITIVE LOGITS
    äºĮä¸ī
    0.07
    Injected
    0.07
    å½ĵä¹ĭ
    0.07
    å¤§æ±Ł
    0.07
    acken
    0.07
    rava
    0.07
     Plum
    0.07
    anen
    0.06
    रà¥ĩ
    0.06
    ä¸įå±Ī
    0.06
    Activations Density 0.048%

    No Known Activations