© 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. 23169
    Prev
    Next
    INDEX
    Explanations

    scattered, sporadic, random, fragmented

    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
     Briggs
    -0.08
    津津
    -0.08
    alie
    -0.07
    书åŁİ
    -0.07
    OPSIS
    -0.07
    _colors
    -0.07
    éĶIJæĦı
    -0.07
    áĥĹ
    -0.07
    ä¸ĢæĻļ
    -0.07
    å£
    -0.07
    POSITIVE LOGITS
     scattered
    0.15
    /random
    0.13
    鼶æĺŁ
    0.13
    æĸŃç»Ń
    0.13
    æķ£çļĦ
    0.13
    spor
    0.12
    ç¢İçīĩ
    0.12
     spor
    0.12
     randomly
    0.12
    random
    0.12
    Activations Density 0.119%

    No Known Activations