© 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. 39289
    Prev
    Next
    INDEX
    Explanations

    arithmetic and logical operations

    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
    Ø©
    -0.09
    Ù°
    -0.08
    enance
    -0.08
    eam
    -0.08
    <decltype
    -0.07
    eba
    -0.07
    ãģŁãĤī
    -0.07
    ablement
    -0.07
    åłĤåłĤ
    -0.07
    ensi
    -0.07
    POSITIVE LOGITS
    åĮ®
    0.08
    ãģ£ãģĵ
    0.07
     اثÙĨÙĬÙĨ
    0.07
    çĿĢçļĦ
    0.07
    semb
    0.07
    åİļçĶŁ
    0.06
    ¼
    0.06
    owski
    0.06
    AspectRatio
    0.06
    isoft
    0.06
    Activations Density 0.001%

    No Known Activations