© 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. 55089
    Prev
    Next
    INDEX
    Explanations

    select then followed

    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
    avs
    -0.07
    è¿IJè¡ĮæĥħåĨµ
    -0.07
     added
    -0.06
     throughout
    -0.06
    æĺ¯ç»ıè¿ĩ
    -0.06
    arya
    -0.06
    微信æī«çłģ
    -0.06
    ogl
    -0.06
    added
    -0.06
    å¸ĥæŀĹ
    -0.06
    POSITIVE LOGITS
    çĦ¶åIJİåĨį
    0.20
     puis
    0.19
    çĦ¶åIJİ
    0.19
    çĦ¶åIJİåľ¨
    0.18
    çĦ¶å¾Į
    0.17
    çĦ¶åIJİæĺ¯
    0.16
    çĦ¶åIJİçĶ¨
    0.16
    çĦ¶åIJİæł¹æį®
    0.15
     followed
    0.15
    çĦ¶åIJİå°Ĩ
    0.15
    Activations Density 0.102%

    No Known Activations