© 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. 12691
    Prev
    Next
    INDEX
    Explanations

    space missions and launches

    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
     eingetragen
    -0.07
    主è¦ģç»ıèIJ¥
    -0.07
    驹
    -0.07
    åħħ
    -0.06
    ä¹ħèĢĮä¹ħä¹ĭ
    -0.06
    åľ¨æ¯ĶèµĽ
    -0.06
    èĶĵ延
    -0.06
    zing
    -0.06
    éĢ¼è¿«
    -0.06
     pervasive
    -0.06
    POSITIVE LOGITS
     manned
    0.09
     maiden
    0.09
     payloads
    0.09
    载人
    0.09
    éĢģä¸Ĭ
    0.08
     succesfully
    0.08
    æľĪçIJĥ
    0.08
     aborted
    0.08
    Reusable
    0.08
     successfully
    0.08
    Activations Density 0.059%

    No Known Activations