© 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. 17087
    Prev
    Next
    INDEX
    Explanations

    itself, collection, commerce, road

    np_acts-logits-general · gemini-2.5-flash-lite

    references to specific fields, disciplines, or specialized domains of activity.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
    lair
    -0.08
    iterals
    -0.08
     RegExp
    -0.08
    èģĶç³»æĪij们
    -0.08
    umfang
    -0.07
    _attrs
    -0.07
    ürg
    -0.07
     Levine
    -0.07
    gehend
    -0.07
    ncia
    -0.07
    POSITIVE LOGITS
     stesso
    0.10
    æľ¬èº«
    0.10
     itself
    0.09
     stessa
    0.09
     stessi
    0.08
     pula
    0.08
     stesse
    0.08
    æľ¬èº«çļĦ
    0.08
    ure
    0.07
    à¹Ģà¸Ĭà¹Īà¸Ļà¸ģัà¸Ļ
    0.07
    Activations Density 1.949%

    No Known Activations