© 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. 16381
    Prev
    Next
    INDEX
    Explanations

    augmentation or expansion

    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
    stroy
    -0.08
    é«ĺ温
    -0.07
    åģļé¢ĺ
    -0.07
    hot
    -0.07
    ightly
    -0.07
    ä¸įæĸŃæıIJé«ĺ
    -0.07
     overd
    -0.07
    alto
    -0.07
    ading
    -0.07
    chn
    -0.07
    POSITIVE LOGITS
    åĽłä¸ºæ²¡æľī
    0.11
     Opportunity
    0.08
    hetto
    0.07
    åĽłä¸ºåıªæľī
    0.07
     kedvez
    0.07
    åĨħ容æıIJä¾Ľæĸ¹
    0.07
    ä¸Ģæİ¢
    0.07
    åıįæŃ£
    0.06
     маленÑĮкой
    0.06
    ÏĦÏģι
    0.06
    Activations Density 0.127%

    No Known Activations