© 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. 15968
    Prev
    Next
    INDEX
    Explanations

    charge

    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
     tallest
    -0.06
    uild
    -0.06
    éĻįèĢĹ
    -0.06
    ç¥ŀåĮ»
    -0.05
    å²Ń
    -0.05
    .fre
    -0.05
     iw
    -0.05
    á»ijt
    -0.05
    Mixed
    -0.05
    éĺŁåijĺ们
    -0.05
    POSITIVE LOGITS
    -elect
    0.09
    edan
    0.08
     ÑĢода
    0.08
    volt
    0.08
    åħ¥éĩij
    0.08
    身份
    0.08
    ihak
    0.08
    kao
    0.08
    .checkbox
    0.08
    -ion
    0.08
    Activations Density 0.001%

    No Known Activations