© 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. 58280
    Prev
    Next
    INDEX
    Explanations

    "thus"

    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
    ogi
    -0.08
    aiser
    -0.08
    éĤ£åı¯æĺ¯
    -0.07
    éĤ£åı¯
    -0.07
    çĦ¶å¤§
    -0.07
     ale
    -0.07
     ê·¸ëłĩì§Ģ
    -0.07
    éĢĶ
    -0.07
    ç°¿
    -0.07
    oga
    -0.06
    POSITIVE LOGITS
    éĹ®é¢ĺæĿ¥äºĨ
    0.09
     concludes
    0.08
    解æĥij
    0.08
    以ä¸Ĭå°±æĺ¯
    0.08
    æī©å±ķèµĦæĸĻ
    0.07
    ä¸Ģæĸij
    0.07
    ledes
    0.07
     ë§Īì¹ĺ
    0.07
     ÑģвоеобÑĢаз
    0.07
    å®Įæķ´
    0.07
    Activations Density 0.005%

    No Known Activations