© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29862
    Prev
    Next
    INDEX
    Explanations

    orthogonal design, domain, Med

    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
    é¦ĸå¸Ń
    -0.08
    Trivia
    -0.08
    *Math
    -0.08
    社工
    -0.08
    æĥĬåĸľ
    -0.08
     +/-
    -0.08
    ç²¾åĩĨ
    -0.08
    ç²¾åĩĨçļĦ
    -0.08
    atever
    -0.07
    .createServer
    -0.07
    POSITIVE LOGITS
     supper
    0.07
    åĽ½æ°ijç»ıæµİ
    0.07
    å®ı
    0.07
     occasion
    0.07
     endowed
    0.06
    表达å¼ı
    0.06
    次åºı
    0.06
    æķĻçłĶ室
    0.06
    çŃĶ
    0.06
    åħīæ»ij
    0.06
    Activations Density 0.005%

    No Known Activations