© 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. 48589
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by conjunctions or clauses

    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
    çļĦ人äºĨ
    -0.07
    hte
    -0.07
    以åıĬå¦Ĥä½ķ
    -0.07
     казалоÑģÑĮ
    -0.07
    æģ°æģ°
    -0.07
    以èĩ³
    -0.07
    elingen
    -0.07
    iche
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    åıĬéħį件
    -0.06
    POSITIVE LOGITS
     whereas
    0.12
     Ø£Ùħا
    0.11
     sedangkan
    0.10
     Sedangkan
    0.10
    èĢĮéĤ£äºĽ
    0.10
    èĢĮ
    0.10
     natomiast
    0.10
     tandis
    0.09
    èĢĮåħ¶ä»ĸ
    0.09
     Còn
    0.09
    Activations Density 0.456%

    No Known Activations