© 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. 40005
    Prev
    Next
    INDEX
    Explanations

    text again suggestion

    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
    hors
    -0.08
    Ùħائ
    -0.08
    leden
    -0.07
    almente
    -0.07
    éģĵæĿ¥
    -0.07
    AFX
    -0.07
     {[
    -0.07
    éĴĵ
    -0.07
    .insertBefore
    -0.07
     xmlns
    -0.07
    POSITIVE LOGITS
     nữa
    0.08
    æİ¥çĿĢ
    0.08
    ours
    0.07
    å·²ç»ıè¿ŀç»Ń
    0.07
    è¿ŀç»Ń
    0.07
     lagi
    0.07
     continu
    0.06
    æĽ´æĺ¯
    0.06
     perk
    0.06
    åıĪä¸Ģ个
    0.06
    Activations Density 0.039%

    No Known Activations