© 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. 47896
    Prev
    Next
    INDEX
    Explanations

    storage and condition

    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
    .Context
    -0.07
    issi
    -0.07
    pis
    -0.07
    ibi
    -0.07
     Proposed
    -0.07
    èĢĢçľ¼
    -0.07
    åħ³
    -0.07
     Pangan
    -0.07
    ç½ijç«Ļå¤ĩæ¡Ī
    -0.07
     approaches
    -0.07
    POSITIVE LOGITS
     delicate
    0.10
    æĿ¥ä¹ĭä¸įæĺĵ
    0.07
    å¼Ģå°ģ
    0.07
    ä¿Ŀåħ»
    0.07
    èĦĨå¼±çļĦ
    0.07
    çļĦ使çĶ¨å¯¿åij½
    0.07
     delikat
    0.07
    æľĢæĸ°è¯Ħ论
    0.07
    ãģĽãģ£ãģĭãģı
    0.07
    å¨ĩ
    0.07
    Activations Density 0.081%

    No Known Activations