© 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. 45361
    Prev
    Next
    INDEX
    Explanations

    cement / factor

    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
    quel
    -0.08
    åĪ©çī©
    -0.08
    tas
    -0.07
    åĿĬ
    -0.07
    oly
    -0.07
    elan
    -0.07
    _parameters
    -0.07
    _RESOURCES
    -0.07
    Vent
    -0.06
    isto
    -0.06
    POSITIVE LOGITS
    ä¸į论æĺ¯
    0.08
    ä½İä½į
    0.08
    ç»®
    0.07
     изÑĭÑģка
    0.07
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.07
    綺
    0.07
    å¦Īå¦Ī们
    0.07
    AdapterFactory
    0.07
    ynet
    0.07
    主è¦ģæľī
    0.07
    Activations Density 0.844%

    No Known Activations