© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34923
    Prev
    Next
    INDEX
    Explanations

    onCreate constructor

    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
    Negative Logits
    æµ·æ¶Ľ
    -0.08
    arkin
    -0.08
    ноÑģÑĤей
    -0.07
    åĸľæĢĴåĵĢ
    -0.07
    æĻĸ
    -0.07
    roj
    -0.07
    akon
    -0.07
    _RPC
    -0.07
    ä¸Ģ缮
    -0.07
    OnInit
    -0.07
    POSITIVE LOGITS
    microsoft
    0.07
    Ñħам
    0.07
     Middleton
    0.06
    ç½
    0.06
    ế
    0.06
     Sherman
    0.06
    æī©å±ķèµĦæĸĻ
    0.06
    ãģ°ãģĭãĤĬ
    0.06
    ses
    0.06
     Orr
    0.06
    Activations Density 0.005%

    No Known Activations