© 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. 17758
    Prev
    Next
    INDEX
    Explanations

    finding a missing element

    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
    æľīçļĦ
    -0.07
    æĺ¯è¦ģ
    -0.07
     gee
    -0.07
    ledger
    -0.06
    æŁĵ
    -0.06
    æĺ¯æľī
    -0.06
    Ùħر
    -0.06
    ä½Ĩæĺ¯å¯¹äºİ
    -0.06
    æĶ¶åĽŀ
    -0.06
    onie
    -0.06
    POSITIVE LOGITS
    é¡·
    0.08
    ponce
    0.07
    kilde
    0.07
    ä¸įæ²»
    0.07
    edback
    0.07
    jeÄį
    0.07
    ī¬
    0.07
    posito
    0.07
     berkat
    0.07
    pires
    0.07
    Activations Density 0.004%

    No Known Activations