© 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. 19579
    Prev
    Next
    INDEX
    Explanations

    DNA base pairing and mismatches

    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
    antil
    -0.08
    ä¸ĢæıIJ
    -0.07
    enburg
    -0.07
    æĿĢæ°Ķ
    -0.06
    ven
    -0.06
    nen
    -0.06
    ennes
    -0.06
    ùn
    -0.06
    Epoch
    -0.06
    è¾ĵåĩºåĬŁçİĩ
    -0.06
    POSITIVE LOGITS
    éħį
    0.10
    éħį对
    0.09
    çī¢åĽº
    0.09
     pairing
    0.08
     زÙĪج
    0.08
    pair
    0.08
     pairs
    0.08
     opposite
    0.07
    ä¸Ģ对ä¸Ģ
    0.07
     standards
    0.07
    Activations Density 0.003%

    No Known Activations