© 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. 57832
    Prev
    Next
    INDEX
    Explanations

    materials and components

    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
     presumably
    -0.09
     pula
    -0.08
     BOTH
    -0.08
     roughly
    -0.08
     essentially
    -0.08
    dds
    -0.08
     EITHER
    -0.07
    çĬ¹å¦Ĥ
    -0.07
     either
    -0.07
     basically
    -0.07
    POSITIVE LOGITS
     czy
    0.12
    æĸ¹ãĤĦ
    0.11
    æĸĩ件æĪĸ
    0.11
    人ãĤĦ
    0.11
    ìĸ´ëĤĺ
    0.10
    ãĤĵãģłãĤĬ
    0.10
    ãģĹãģŁãĤĬ
    0.10
    ä¹ĭäºİ
    0.10
    人æĪĸ
    0.10
    ãģĦãģŁãĤĬ
    0.10
    Activations Density 0.302%

    No Known Activations