© 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. 64332
    Prev
    Next
    INDEX
    Explanations

    by-products or measured compounds

    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
    æīİæīİå®ŀ
    -0.07
    el
    -0.07
    om
    -0.07
    åĩĢæµģåħ¥
    -0.07
    缴æݥ被
    -0.06
    oller
    -0.06
    +xml
    -0.06
    odem
    -0.06
    zza
    -0.06
    èĢĮä¸įæĺ¯
    -0.06
    POSITIVE LOGITS
    Ctr
    0.08
    ä¸įæĺİçĻ½
    0.07
    pbs
    0.07
    egue
    0.07
    kina
    0.07
     веÑīÑĮ
    0.07
    屿
    0.07
    èmes
    0.07
    ÙĬÙĥ
    0.07
    ijing
    0.06
    Activations Density 0.643%

    No Known Activations