© 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. 65305
    Prev
    Next
    INDEX
    Explanations

    Denied

    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
    yta
    -0.07
    esm
    -0.07
    æı£
    -0.07
    à¹Īวม
    -0.07
    çĤ¹åĩ»ä¸ĭè½½
    -0.07
    ÑĢеменно
    -0.07
    ÙĴÙĬ
    -0.07
    åį§é¾Ļ
    -0.06
    ENDA
    -0.06
    åѤç«ĭ
    -0.06
    POSITIVE LOGITS
    大æ¦Ĥåľ¨
    0.12
    å¤§çº¦åľ¨
    0.11
    æĺ¯ä»Ģä¹ĪæŶåĢĻ
    0.11
    è¦ģåĪ°
    0.10
     earliest
    0.10
    ä»Ģä¹ĪæŶåĢĻ
    0.10
     spätestens
    0.10
     ìĸ¸ìłľ
    0.09
    å°Ĩäºİ
    0.09
    æľŁéĻIJ为
    0.09
    Activations Density 0.338%

    No Known Activations