© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16214
    Prev
    Next
    INDEX
    Explanations

    action and state suffixes

    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
    们çļĦ
    -0.08
     undergoing
    -0.07
    ities
    -0.07
    walker
    -0.07
    ä¹ĭä¸ĢçļĦ
    -0.07
    -sized
    -0.06
    们
    -0.06
    ships
    -0.06
    (s
    -0.06
    åĭ¤
    -0.06
    POSITIVE LOGITS
    à¹ģละà¸ģาร
    0.12
    åĭĩå¾Ģ缴åīį
    0.10
     ulang
    0.10
     Ùħجدد
    0.10
    åĬłæĭ¿å¤§
    0.10
    گرÛĮ
    0.09
    /rec
    0.09
    缸è¾ħ缸æĪIJ
    0.09
     avven
    0.09
    åıijçĶŁåľ¨
    0.09
    Activations Density 0.017%

    No Known Activations