© 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. 23357
    Prev
    Next
    INDEX
    Explanations

    quantityamountmass

    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
     wherever
    -0.07
    çĺŁ
    -0.07
    涯
    -0.07
    éĤ£ä¹ĪæĪij们
    -0.06
    RefCount
    -0.06
    (getString
    -0.06
    ulis
    -0.06
    URT
    -0.06
    ilib
    -0.06
    argc
    -0.06
    POSITIVE LOGITS
     جراء
    0.08
     per
    0.08
    /display
    0.08
    /respond
    0.07
    adra
    0.07
    /not
    0.07
    /generated
    0.07
    ellan
    0.07
    åĿ
    0.07
     dợ
    0.07
    Activations Density 0.077%

    No Known Activations