© 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. 27187
    Prev
    Next
    INDEX
    Explanations

    gone, disappeared, or away

    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
    çĶŁçī©ç§ijæĬĢ
    -0.07
    çĿĢæĪijçļĦ
    -0.07
    äºİ人
    -0.07
    GI
    -0.07
    witz
    -0.07
    éļħ
    -0.07
    çĿĢæĪij
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    çĿĢå°ı
    -0.07
    cach
    -0.07
    POSITIVE LOGITS
    åıĸèĢĮ代ä¹ĭ
    0.13
    æ®Ĩå°½
    0.13
    踪影
    0.09
    åıªåī©
    0.09
    åıªåī©ä¸ĭ
    0.09
     entirely
    0.09
     replaced
    0.09
     nhÆ°á»Ŀng
    0.08
     altogether
    0.08
    èį¡
    0.08
    Activations Density 0.150%

    No Known Activations