© 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. 11336
    Prev
    Next
    INDEX
    Explanations

    postal codes

    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
     rever
    -0.08
    念念
    -0.07
    rever
    -0.07
    ÏĥÏĦε
    -0.07
    çļĦäºĭä¸ļ
    -0.07
    oire
    -0.07
    åĴĮåIJĮåѦ
    -0.07
     dep
    -0.06
    irik
    -0.06
    ä¾µ
    -0.06
    POSITIVE LOGITS
    οδο
    0.08
    太çĻ½
    0.08
    æĺ¥å¤ıç§ĭåĨ¬
    0.08
    eliac
    0.07
    keyp
    0.07
    ξειÏĤ
    0.07
    оÑħÑĢа
    0.07
    ãĤģãģIJ
    0.07
    Charsets
    0.07
     rowData
    0.07
    Activations Density 0.035%

    No Known Activations