© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48435
    Prev
    Next
    INDEX
    Explanations

    album, OK, EXIT

    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
    åIJĦåŃ¦æł¡
    -0.06
    åĬ¨æīĭèĥ½åĬĽ
    -0.06
    áĥĺáĥĹ
    -0.06
    éķ¿æĮīè¯ĨåĪ«äºĮç»´çłģ
    -0.06
     revan
    -0.06
    æĪIJæŃ£
    -0.06
    ä¹Łæĺ¯éľĢè¦ģ
    -0.06
    ÐłÐ¡
    -0.06
     Elementary
    -0.05
    ouser
    -0.05
    POSITIVE LOGITS
    minster
    0.09
     Loads
    0.08
    niers
    0.07
     loa
    0.07
    htub
    0.07
    æľ
    0.07
    /loader
    0.07
    strup
    0.07
    fter
    0.07
    ä¹ĭæĢ¥
    0.07
    Activations Density 0.374%

    No Known Activations