© 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. 10788
    Prev
    Next
    INDEX
    Explanations

    backward backward backward reverse retrograde

    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
    Ïĥια
    -0.08
    ady
    -0.08
    åĩºæĿ¥åIJİ
    -0.08
     Kee
    -0.07
    orten
    -0.07
    ä¸ĵä¸ļåŃ¦æł¡
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    olley
    -0.07
    æĽ¿ãģĪ
    -0.07
    æĸ°åĮº
    -0.07
    POSITIVE LOGITS
     backwards
    0.14
     backward
    0.13
    backward
    0.12
    (reverse
    0.11
    éĢĨåIJij
    0.11
     revers
    0.10
    (back
    0.09
     Reverse
    0.09
    reverse
    0.09
    åĽŀåİ»
    0.09
    Activations Density 0.029%

    No Known Activations