© 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. 7134
    Prev
    Next
    INDEX
    Explanations

    such as

    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
    缸å½ĵ
    -0.08
    ermen
    -0.08
    ä¸Ģèµ·
    -0.08
    åįģåĪĨ
    -0.07
    ALAR
    -0.07
    è¿Ľç¾¤
    -0.07
    å±
    -0.07
    æī§
    -0.07
     <![
    -0.07
    ÙĴÙĥ
    -0.07
    POSITIVE LOGITS
    象
    0.06
    çĻ½æ°´
    0.06
    S
    0.06
    æŦ
    0.06
    æĶ¯åĩº
    0.06
    Ñĩок
    0.06
    opsis
    0.06
     doj
    0.06
    ç«¥åŃIJ
    0.05
    zend
    0.05
    Activations Density 0.001%

    No Known Activations