© 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. 19652
    Prev
    Next
    INDEX
    Explanations

    technical context or definition

    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
    éĥ¨éŨèģĶåIJĪ
    -0.07
    æłijä¸Ģ
    -0.07
    å¤Ħäºİ
    -0.06
    ä¹ĭçĪ¶
    -0.06
    ç«ĭäºİ
    -0.06
    ostr
    -0.06
     ok
    -0.06
    ãĥIJãĥ©
    -0.06
    è´¹çĶ¨çĶ±
    -0.06
    æĬ«
    -0.06
    POSITIVE LOGITS
     definition
    0.08
    arina
    0.08
    ÑĢÑĥжи
    0.08
    æľīçļĦåIJĮåѦ
    0.07
     supposedly
    0.07
    definition
    0.07
    æ°¸å®ļ
    0.07
    ึà¸ĩ
    0.07
    κει
    0.07
     formula
    0.07
    Activations Density 0.129%

    No Known Activations