© 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. 22465
    Prev
    Next
    INDEX
    Explanations

    purpose or intention

    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¸įæĺ¯åĽłä¸º
    -0.07
    ötz
    -0.07
    æĺ¯åĽłä¸º
    -0.07
    æł¹æį®åĽ½å®¶
    -0.07
    	Me
    -0.06
     demos
    -0.06
    aglia
    -0.06
    ä¸įä»ħä»ħæĺ¯
    -0.06
    æŃ£æĺ¯åĽłä¸º
    -0.06
    atrice
    -0.06
    POSITIVE LOGITS
    igans
    0.07
    ercul
    0.07
    æľīè¯Ŀ
    0.07
    ëŀĺ
    0.07
     nevertheless
    0.07
    onth
    0.07
    rint
    0.07
    elmi
    0.06
     Bun
    0.06
    oust
    0.06
    Activations Density 1.078%

    No Known Activations