© 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. 1813
    Prev
    Next
    INDEX
    Explanations

    related to

    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
     magari
    -0.10
    ych
    -0.08
    åĵªæĢķæĺ¯
    -0.08
    ç½ijåıĭè¯Ħ论
    -0.08
     vorba
    -0.08
    å²Ĥä¸įæĺ¯
    -0.08
    æŁIJä¸Ģ天
    -0.08
    å°±ç®ĹäºĨ
    -0.07
    æ³¥çŁ³
    -0.07
    éĶ¦ç»£
    -0.07
    POSITIVE LOGITS
     therefore
    0.10
     bowiem
    0.10
     infatti
    0.10
     inoltre
    0.10
     übrigens
    0.09
     furthermore
    0.08
    l
    0.08
     totiž
    0.08
    ogl
    0.08
    åĽłæѤ
    0.08
    Activations Density 1.984%

    No Known Activations