© 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. 17604
    Prev
    Next
    INDEX
    Explanations

    Ni or RT

    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
    achers
    -0.07
     generation
    -0.07
     accum
    -0.07
    举
    -0.07
     Gener
    -0.06
    Gener
    -0.06
     اÙĦتس
    -0.06
     period
    -0.06
    _MAG
    -0.06
    мÑıн
    -0.06
    POSITIVE LOGITS
    flix
    0.09
    elib
    0.08
     Transitional
    0.08
    adol
    0.08
    unes
    0.07
    auge
    0.07
    秫
    0.07
    å¤ļæīį
    0.07
    assa
    0.07
    ktor
    0.07
    Activations Density 0.001%

    No Known Activations