© 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. 9004
    Prev
    Next
    INDEX
    Explanations

    finally ending sequences

    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
     lucky
    -0.07
    åľ¨æŁIJ
    -0.07
    ä¸ĬäºĨä¸Ģ
    -0.07
    Fal
    -0.07
    ouw
    -0.07
    åĩºå¥ĩ
    -0.07
    çıĬ
    -0.06
    缴æİ¥
    -0.06
    çļĦåŁºæľ¬
    -0.06
    azine
    -0.06
    POSITIVE LOGITS
     finally
    0.11
    å§Ĺå§Ĺ
    0.10
    finally
    0.09
     afterward
    0.09
     enfin
    0.09
    à¸Ħà¹Īà¸Ńย
    0.09
    à¸Ĺี
    0.09
    çĦ¶åIJİåĨį
    0.08
    æľĢåIJİæĺ¯
    0.08
     Finally
    0.08
    Activations Density 0.110%

    No Known Activations