© 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. 32488
    Prev
    Next
    INDEX
    Explanations

    passwords or pins

    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
    паÑħ
    -0.08
    ÙĪØ·
    -0.08
    º
    -0.08
    ACA
    -0.08
    缴æİ¥å°Ĩ
    -0.08
    åIJŀåĻ¬
    -0.07
    λÏīν
    -0.07
    stown
    -0.07
    encontre
    -0.07
    oya
    -0.07
    POSITIVE LOGITS
     exact
    0.08
    Precision
    0.08
    precision
    0.08
     Precision
    0.08
    exact
    0.08
    精确
    0.08
     precision
    0.08
     value
    0.07
     precise
    0.07
     decimal
    0.07
    Activations Density 0.002%

    No Known Activations