© 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. 25749
    Prev
    Next
    INDEX
    Explanations

    words containing common roots

    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
    常çĶ¨
    -0.07
    amen
    -0.06
    çļ®çļĦ
    -0.06
    对å¾ħ
    -0.06
    aken
    -0.06
     stretched
    -0.06
     شدÙĨ
    -0.06
    è¼
    -0.06
    å®ŀçļĦ
    -0.06
    åĽŃçļĦ
    -0.06
    POSITIVE LOGITS
    _backend
    0.09
    åİ»åĵªåĦ¿
    0.08
    ToPoint
    0.08
    ept
    0.08
    ä¸IJ
    0.08
    olja
    0.07
    mű
    0.07
    दार
    0.07
    åĸĥ
    0.07
    klass
    0.07
    Activations Density 0.403%

    No Known Activations