© 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. 2036
    Prev
    Next
    INDEX
    Explanations

    sort in decreasing order

    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
    ott
    -0.07
    ane
    -0.07
    ez
    -0.06
    oth
    -0.06
    æ´
    -0.06
    访
    -0.06
    quad
    -0.06
    erg
    -0.06
    #else
    -0.06
    eme
    -0.06
    POSITIVE LOGITS
    缸åħ³æݨèįIJ
    0.08
    _tD
    0.07
    ecraft
    0.07
    便è¦ģ
    0.07
    kena
    0.07
    æīĢå±ŀåĪĨç±»
    0.07
    isir
    0.07
    çĤ¹è¿ĻéĩĮ
    0.07
    mey
    0.07
    º¼
    0.07
    Activations Density 0.061%

    No Known Activations