© 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. 48154
    Prev
    Next
    INDEX
    Explanations

    contrast and conjunctions

    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
    ouw
    -0.08
    emd
    -0.07
    porte
    -0.07
    umbu
    -0.07
    ouver
    -0.07
    è¿Ŀåıįä¸Ĭè¿°
    -0.07
    Messaging
    -0.07
    asant
    -0.07
    èĮ¬
    -0.07
    éĢļè¿ĩåľ¨
    -0.07
    POSITIVE LOGITS
    çŃīçŃī
    0.09
    ...**
    0.07
    ullet
    0.06
    âĢ¦*
    0.06
    éªı
    0.06
    âĢ¦**
    0.06
    yc
    0.06
    hand
    0.06
    iba
    0.06
    —all
    0.06
    Activations Density 0.223%

    No Known Activations