© 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. 16023
    Prev
    Next
    INDEX
    Explanations

    comma then conjunction or clause

    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
    iné
    -0.09
    ÄĽÅ¾
    -0.08
    å¨Ĩ
    -0.08
    adang
    -0.08
    ·
    -0.07
    ãģĿãģ®ãĤĪãģĨãģª
    -0.07
    è°ģæĺ¯
    -0.07
    MDB
    -0.07
     Furthermore
    -0.07
    iku
    -0.07
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.09
    æĸ°åĬłåĿ¡
    0.08
    éĺ¿æĭī伯
    0.08
    缸è¾ħ缸æĪIJ
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    à¹Ģลย
    0.07
     thus
    0.07
    en
    0.07
     therefore
    0.07
    æĭīçļĦ
    0.07
    Activations Density 0.005%

    No Known Activations