© 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. 12836
    Prev
    Next
    INDEX
    Explanations

    The Departed stars

    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
    ä»ĸå°±æĺ¯
    -0.08
    bote
    -0.08
    кÑĤи
    -0.08
    eng
    -0.08
    วà¸ĩ
    -0.07
     rtrim
    -0.07
    纺ç»ĩæľįè£ħ
    -0.07
    管çIJĨåĽ¢éĺŁ
    -0.07
    perf
    -0.07
    ä¿¡è¾¾
    -0.07
    POSITIVE LOGITS
    лÑĥÑĩ
    0.06
    åľ¨è¿Ļ
    0.06
    ãģĭãĤı
    0.06
    æį®
    0.06
     mul
    0.06
    YC
    0.06
     rel
    0.05
     vere
    0.05
    ighbor
    0.05
     reportedly
    0.05
    Activations Density 0.062%

    No Known Activations