© 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. 26746
    Prev
    Next
    INDEX
    Explanations

    GitHub, India, DST, local, oral, admin

    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
    åľ°åľ¨
    -0.11
    æĬĢæľ¯åľ¨
    -0.10
    å·¥ä½ľä¸ŃçļĦ
    -0.10
    缮åīįåľ¨
    -0.10
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    -0.09
    æĤ£èĢħåľ¨
    -0.09
    åľ¨å·¥ä½ľ
    -0.09
    çŃīåľ¨
    -0.09
    å®¶åľ¨
    -0.09
    åħ¶ä¸ŃçļĦ
    -0.09
    POSITIVE LOGITS
    åĮ»çĶŁæĮĩ导ä¸ĭ
    0.10
    åĮ»çĶŁçļĦæĮĩ导ä¸ĭ
    0.10
     ×ķ×ij
    0.10
    èĮĥåĽ´åĨħ
    0.09
     midst
    0.09
    ä»Ģä¹Īåľ°æĸ¹
    0.09
    ä¸Ĭè¿Ľè¡Į
    0.09
     entirety
    0.09
    å±ĤéĿ¢ä¸Ĭ
    0.09
     Ú©ÛIJ
    0.09
    Activations Density 0.007%

    No Known Activations