© 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. 28114
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions like but, yet

    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
    sWith
    -0.13
    ìį¨
    -0.11
    ãģĦãĤĭ
    -0.10
    s
    -0.10
    schen
    -0.10
    scher
    -0.09
    à¸Ļิà¸ĺิ
    -0.09
    ted
    -0.09
    swith
    -0.09
    texte
    -0.08
    POSITIVE LOGITS
    ãģªãģĮãĤī
    0.10
    ого
    0.10
    åIJ¦
    0.09
    ам
    0.09
    ãģĺãĤģãģ¦
    0.08
    ä½łåį´
    0.08
    à¸ģà¹Į
    0.08
    ãģ£ãģįãĤĬ
    0.08
    elor
    0.08
    upported
    0.08
    Activations Density 0.002%

    No Known Activations