© 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. 1685
    Prev
    Next
    INDEX
    Explanations

    combining/aggregating things

    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
    ä¸įä¸ĭåİ»
    -0.09
    åIJĦæĸ¹
    -0.08
    å·¦åı³
    -0.08
    å·¡è§Ĩåijĺ
    -0.08
    /html
    -0.08
    å¾ĭ
    -0.08
    utto
    -0.07
    ambi
    -0.07
    ierre
    -0.07
    Mui
    -0.07
    POSITIVE LOGITS
     together
    0.10
    åľ¨ä¸Ģèµ·
    0.09
     collectively
    0.08
    åľ¨ä¸Ģèµ·çļĦ
    0.08
    åIJĪãĤıãģĽãģŁ
    0.08
    ä¸Ģèµ·
    0.08
     their
    0.08
     Together
    0.07
    ãģ¾ãģ¨ãĤģãģ¦
    0.07
    åħ±åIJĮ为
    0.07
    Activations Density 0.078%

    No Known Activations