© 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. 34514
    Prev
    Next
    INDEX
    Explanations

    associated with events or places

    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
    ki
    -0.07
     sint
    -0.06
    goo
    -0.06
     piet
    -0.06
    _cores
    -0.06
    rones
    -0.06
    ä¸ŃåİŁ
    -0.06
    .apple
    -0.06
    kle
    -0.06
     Braves
    -0.06
    POSITIVE LOGITS
    -associated
    0.11
    对åºĶçļĦ
    0.10
    çĽ¸å¯¹åºĶçļĦ
    0.09
    associated
    0.08
    -related
    0.08
    ãģ«å¯¾å¿ľ
    0.08
    åħ³èģĶæĢ§
    0.08
    身边
    0.08
    è¾ħ导
    0.08
    éľĢè¦ģåIJĮ
    0.08
    Activations Density 0.295%

    No Known Activations