© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52052
    Prev
    Next
    INDEX
    Explanations

    multiple choice answers

    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
    Negative Logits
    ÙĬØ©
    -0.07
     âĶľâĶĢâĶĢ
    -0.07
     ↵            ↵
    -0.07
    çݺ
    -0.07
    ale
    -0.07
    anson
    -0.07
    æĦŁåįģ足
    -0.07
    ation
    -0.07
    Ø©
    -0.07
    ertz
    -0.06
    POSITIVE LOGITS
    åij½
    0.09
     ãģªãģ©
    0.07
    etti
    0.07
    åĨįèĢħ
    0.07
    è¿ĺæľīå°±æĺ¯
    0.07
    osso
    0.07
    بت
    0.07
    ogg
    0.07
     dbc
    0.06
    ijnen
    0.06
    Activations Density 0.008%

    No Known Activations