© 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. 42645
    Prev
    Next
    INDEX
    Explanations

    programmed to, wash and, Addition of, get within, another

    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
    èĢĮå¾ĹåIJį
    -0.08
    åı¯æĥ³
    -0.08
    گاÙĨ
    -0.07
     ÏĥÏħνο
    -0.07
    ØŃاد
    -0.07
    çģ«è¾£
    -0.07
    è¿ĺæľīå°±æĺ¯
    -0.07
    åIJĮæĹ¶ä¹Łåı¯ä»¥
    -0.07
    ä»ĸçĶļèĩ³
    -0.07
    å°ijèµ°
    -0.06
    POSITIVE LOGITS
    åıĪä¼ļ
    0.08
     же
    0.08
    å°ĨæѤ
    0.08
    æīĵçł´äºĨ
    0.08
    chter
    0.08
    åĪĻå°Ĩ
    0.08
    åıĪæĺ¯
    0.08
     मातà¥įर
    0.08
    对ä¸Ĭè¿°
    0.08
    åį´è®©
    0.08
    Activations Density 0.268%

    No Known Activations