© 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. 42626
    Prev
    Next
    INDEX
    Explanations

    linking clauses and phrases

    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
    ophil
    -0.07
    abal
    -0.07
    åħ¶éģĵ
    -0.07
    æīĢ使çĶ¨çļĦ
    -0.07
    çľĭæĪIJ
    -0.07
    arious
    -0.07
    åģ¶
    -0.07
    odal
    -0.06
    erman
    -0.06
    æł¹æį®ä¸įåIJĮ
    -0.06
    POSITIVE LOGITS
    ä½ķåĨµ
    0.10
    è¿ĻéĩĮ
    0.10
    åľ¨è¿ĻéĩĮ
    0.09
    è¿ĻéĩĮæĺ¯
    0.08
     ours
    0.08
    åľ¨æŃ¤æ¬¡
    0.08
    对äºİè¿Ļ个
    0.08
    æĽ´ä½ķåĨµ
    0.08
     here
    0.08
    è¿ĻéĩĮæľī
    0.08
    Activations Density 0.117%

    No Known Activations