© 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. 65413
    Prev
    Next
    INDEX
    Explanations

    .com domain names

    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
    å¦Ĥä¸Ģ
    -0.08
    åŃ¦ä»¥èĩ´çĶ¨
    -0.07
    zell
    -0.07
    agu
    -0.07
    å¦ĤçĶ»
    -0.07
    uluh
    -0.06
    峪
    -0.06
     revolving
    -0.06
    allar
    -0.06
    getto
    -0.06
    POSITIVE LOGITS
    ulti
    0.07
    odyn
    0.07
    asier
    0.07
    earer
    0.07
    é½
    0.07
    åıĪ以
    0.07
    ä¸įæŃ»
    0.07
    SA
    0.07
     kindness
    0.07
    èģ
    0.06
    Activations Density 0.002%

    No Known Activations