© 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. 12217
    Prev
    Next
    INDEX
    Explanations

    partly others have

    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
    evin
    -0.07
    bst
    -0.07
    aria
    -0.07
    çݰ代åĮĸ建设
    -0.07
    pos
    -0.07
    ä¸ĢæĿ¡é¾Ļ
    -0.07
     velit
    -0.07
    ioni
    -0.07
    çļĦæŃĮ
    -0.07
    车åĴĮ
    -0.07
    POSITIVE LOGITS
     downright
    0.07
    ä½łä¸įçŁ¥éģĵ
    0.07
    å·§
    0.07
    ä½łçľĭçľĭ
    0.07
     ones
    0.07
    .TryParse
    0.06
    åħ¶
    0.06
    ä¹ĥ
    0.06
    åĵį
    0.06
    åħ¶ä»ĸ
    0.06
    Activations Density 0.756%

    No Known Activations