© 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. 51147
    Prev
    Next
    INDEX
    Explanations

    copyright and license

    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
    ?'
    -0.07
    ä¹ĭåīįåľ¨
    -0.07
    çĶļèĩ³æĺ¯
    -0.07
    èģļ
    -0.06
    åIJ¸å¼ķ
    -0.06
    åħĪåīį
    -0.06
    é¼ĵ
    -0.06
    åıªèĥ½
    -0.06
    mob
    -0.06
    ä¹ĭåīį
    -0.06
    POSITIVE LOGITS
    æ°¸è¿ľçļĦ
    0.08
    åīįèĮħ
    0.08
    åĬłåħ³æ³¨
    0.08
    ä¸Ģ读
    0.07
    æľĢçĪ±
    0.07
    ÙĥÙĪ
    0.07
    utations
    0.07
    ä¼ģä¸ļåıĬ
    0.07
    å¿ħ读
    0.07
    åģļçļĦäºĭ
    0.07
    Activations Density 0.002%

    No Known Activations