© 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. 42026
    Prev
    Next
    INDEX
    Explanations

    size and quantity modifiers

    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
    åĴĮæĦıä¹ī
    -0.09
    estas
    -0.08
    agens
    -0.08
    æ·ij女
    -0.08
    ãĥĭãĥ³ãĤ°
    -0.07
    beck
    -0.07
    zir
    -0.07
    åħ¼æĢ»ç»ıçIJĨ
    -0.07
    ẽ
    -0.07
    /value
    -0.07
    POSITIVE LOGITS
    -sized
    0.08
    ly
    0.08
    大å°ıçļĦ
    0.07
     sized
    0.07
    åħ¶
    0.07
     chiá»ģu
    0.06
     diá»ĩn
    0.06
    èĨ³
    0.06
     [{'
    0.06
    à¸Ħวาม
    0.06
    Activations Density 0.356%

    No Known Activations