© 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. 42752
    Prev
    Next
    INDEX
    Explanations

    sentence endings followed by start words

    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
    matter
    -0.07
    alia
    -0.07
    ä½Ĩæĺ¯ä½ł
    -0.07
    æŃ£
    -0.07
    çļĦæŃ£
    -0.06
    \/\/
    -0.06
     matter
    -0.06
    ited
    -0.06
    çŁ¢
    -0.06
    emic
    -0.06
    POSITIVE LOGITS
    джи
    0.08
    羣æľī
    0.08
    æī©å±ķèµĦæĸĻ
    0.07
     mú
    0.07
    uali
    0.07
    ç©¿ä¸ĬäºĨ
    0.07
    å±ħäºİ
    0.07
    igham
    0.07
    iever
    0.07
    ç»Īç»ĵ
    0.07
    Activations Density 0.012%

    No Known Activations