© 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. 59049
    Prev
    Next
    INDEX
    Explanations

    details explanation recap review spoiler current

    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
    åı¯æĮģç»Ńåıijå±ķ
    -0.06
    è¿Ļä¹Ł
    -0.06
     Tradition
    -0.06
     tard
    -0.06
    anche
    -0.06
    侦
    -0.06
    åı¯æĮģç»Ń
    -0.06
    å½ĵ羣
    -0.06
    äºijéľĦ
    -0.06
    ä½łçļĦæľĭåıĭ
    -0.06
    POSITIVE LOGITS
    etails
    0.09
     details
    0.09
    details
    0.09
    详ç»Ĩæııè¿°
    0.08
    详æĥħ请
    0.08
     déta
    0.08
    ç¯ĩå¹ħ
    0.08
    詳
    0.08
    ç»ĨèĬĤ
    0.08
    详
    0.08
    Activations Density 0.555%

    No Known Activations