© 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. 14085
    Prev
    Next
    INDEX
    Explanations

    steps to create or determine

    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
    tores
    -0.08
     contra
    -0.08
    åĩ¯è¿ª
    -0.08
    contra
    -0.07
    bbc
    -0.07
    ä¸İä¹ĭ
    -0.07
    övet
    -0.07
    å¦ĤæѤ
    -0.07
    çĶļå°ij
    -0.07
    è¶ĬæĿ¥è¶Ĭ好
    -0.07
    POSITIVE LOGITS
    ç¡®å®ļ
    0.08
    etermine
    0.08
    çģ¿
    0.07
     Determine
    0.07
     Identify
    0.07
     Normalize
    0.07
     preliminary
    0.06
    Step
    0.06
     dulu
    0.06
     Convert
    0.06
    Activations Density 0.023%

    No Known Activations