© 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. 8260
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    epass
    -0.08
    åIJĮæĹ¶ä¹Łè¦ģ
    -0.07
    延
    -0.07
    rape
    -0.06
    åIJĮæŶè¦ģ
    -0.06
    _WINDOWS
    -0.06
    estat
    -0.06
    æ±Łå±±
    -0.06
    éĥ½æĺ¯ä¸ĢäºĽ
    -0.06
    Ľ
    -0.06
    POSITIVE LOGITS
     wiÄĻc
    0.10
     therefore
    0.09
     поÑįÑĤомÑĥ
    0.09
    åĽłæѤ
    0.09
    ãģĮãģĤãĤĭãģ®ãģ§
    0.08
    innie
    0.08
     nên
    0.08
     quindi
    0.08
     donc
    0.08
    ãģªãģĦãģ®ãģ§
    0.08
    Activations Density 0.035%

    No Known Activations