© 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. 2608
    Prev
    Next
    INDEX
    Explanations

    random generation

    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
    æ°¸è¿ľçļĦ
    -0.09
     dalje
    -0.07
    avin
    -0.07
    artigen
    -0.07
    strcasecmp
    -0.07
    াত
    -0.07
    ores
    -0.07
    æŁ¥
    -0.07
     natte
    -0.07
    liest
    -0.07
    POSITIVE LOGITS
     random
    0.18
    éļıæľº
    0.17
     randomly
    0.16
     Random
    0.15
    Random
    0.15
    random
    0.15
    -random
    0.13
    _random
    0.12
    =random
    0.12
     randomized
    0.12
    Activations Density 0.282%

    No Known Activations