© 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. 2932
    Prev
    Next
    INDEX
    Explanations

    dates and counts

    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
    -regexp
    -0.08
    _FN
    -0.07
    amation
    -0.07
    ä¸įæŶ
    -0.07
    ogue
    -0.07
    heit
    -0.07
    åľ¨çº¿çķĻè¨Ģ
    -0.07
    次è¦ģ
    -0.07
    第ä¸Ģæī¹
    -0.07
    éĻĽ
    -0.06
    POSITIVE LOGITS
    нÑĥв
    0.07
    åĸµåĸµ
    0.07
    alore
    0.07
    cx
    0.07
    天å°Ĭ
    0.07
     hust
    0.07
    ouns
    0.07
    loader
    0.07
    wab
    0.06
    runner
    0.06
    Activations Density 0.031%

    No Known Activations