© 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. 18599
    Prev
    Next
    INDEX
    Explanations

    experiment application

    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
    éĩİåħ½
    -0.08
    .ms
    -0.07
     deep
    -0.07
     often
    -0.07
    beit
    -0.06
     tight
    -0.06
    brid
    -0.06
    ç§ķ
    -0.06
    夯
    -0.06
     oftmals
    -0.06
    POSITIVE LOGITS
    å®ŀéªĮ
    0.10
    对çħ§ç»Ħ
    0.09
    _experiment
    0.09
     experiment
    0.09
     hypo
    0.09
    æ¯ıç»Ħ
    0.08
    實é©Ĺ
    0.08
    åIJĦç»Ħ
    0.08
    çļĦå®ŀéªĮ
    0.08
    åĩĨå¤ĩäºĨ
    0.08
    Activations Density 0.030%

    No Known Activations