© 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. 10309
    Prev
    Next
    INDEX
    Explanations

    identity fusion, oneness, simultaneously

    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
    ç¬
    -0.08
    eyed
    -0.07
     understandably
    -0.07
     unsuccessfully
    -0.07
     succesfully
    -0.07
     noticeably
    -0.07
     horm
    -0.07
    ordia
    -0.07
    adak
    -0.07
    çĭ¬ç«ĭèĩªä¸»
    -0.07
    POSITIVE LOGITS
    èŀį为ä¸Ģä½ĵ
    0.10
     inse
    0.10
    ä¸Ģä½ĵ
    0.10
     неÑĢаз
    0.10
    ä¸įäºĮ
    0.09
    èŀįåIJĪçļĦ
    0.09
    ä¸Ģä½ĵçļĦ
    0.09
    èŀįåIJĪ
    0.08
     fusion
    0.08
    fusion
    0.08
    Activations Density 0.048%

    No Known Activations