© 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. 12712
    Prev
    Next
    INDEX
    Explanations

    didn't work or success

    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
    ellone
    -0.08
    olin
    -0.08
    oir
    -0.08
    çıĪ
    -0.07
     Instances
    -0.07
    usch
    -0.07
     legitimately
    -0.07
    å²Ĥä¸įæĺ¯
    -0.07
    åıªéľĢ
    -0.07
     potentially
    -0.07
    POSITIVE LOGITS
     nor
    0.08
    nor
    0.08
    æł·çļĦ
    0.08
    æĽ´ä¸įæĺ¯
    0.07
    roe
    0.07
    ä¹Łæ²¡æľī
    0.07
    åĨµä¸Ķ
    0.07
    êt
    0.07
    æľ¬èī²
    0.07
    çľĭä¸įåĩº
    0.06
    Activations Density 0.021%

    No Known Activations