© 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. 7462
    Prev
    Next
    INDEX
    Explanations

    necessary and essential

    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
    以æ¡Ī
    -0.08
    iglia
    -0.08
    ÑĢк
    -0.07
     Verka
    -0.07
    æĿ¥ä¹ĭä¸įæĺĵ
    -0.07
    Äħtek
    -0.07
    çIJĨæĥ³åĴĮ
    -0.07
    æľĢ好æĺ¯
    -0.07
    ancen
    -0.07
    sembler
    -0.07
    POSITIVE LOGITS
     universal
    0.18
     ubiquitous
    0.17
     universally
    0.16
    universal
    0.16
    æĹłå¤Ħä¸įåľ¨
    0.16
    Universal
    0.15
     ÑĥнивеÑĢ
    0.15
    æĹłè®º
    0.15
     Universal
    0.14
     regardless
    0.14
    Activations Density 0.248%

    No Known Activations