© 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. 12921
    Prev
    Next
    INDEX
    Explanations

    everything works

    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
    æł·åŃIJ
    -0.08
    è¾¾ä¸įåĪ°
    -0.07
     Ø£ÙĪÙĦاÙĭ
    -0.07
    istor
    -0.07
     whole
    -0.07
    åħ¨ä½ĵãģ®
    -0.07
    dd
    -0.07
    ä¿ł
    -0.07
     Whole
    -0.07
    ç©
    -0.07
    POSITIVE LOGITS
    åĮ¹éħį
    0.07
    Unhandled
    0.07
    .aspect
    0.07
    BAL
    0.07
    gens
    0.07
    acca
    0.07
    éĩijæĸ¯
    0.07
    azar
    0.07
    åĪģ
    0.06
    udara
    0.06
    Activations Density 0.013%

    No Known Activations