© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60592
    Prev
    Next
    INDEX
    Explanations

    completeness and detailed information

    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
    cus
    -0.07
    æ¯Ķãģ¹ãĤĭãģ¨
    -0.07
    colo
    -0.07
    akis
    -0.07
    æĸ¹å¼ı
    -0.07
    mps
    -0.07
    å°Ĩä½ł
    -0.07
    ç»ĦåIJĪ
    -0.07
    è¦ģ积æŀģ
    -0.07
    oes
    -0.06
    POSITIVE LOGITS
    对æѤ
    0.09
    å°±æѤ
    0.07
    gether
    0.07
    å°įæѤ
    0.06
    oll
    0.06
    彦
    0.06
    对è¿Ļ个
    0.06
    egra
    0.06
     titled
    0.06
    è¿Ļæĸ¹éĿ¢çļĦ
    0.06
    Activations Density 0.006%

    No Known Activations