© 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. 17643
    Prev
    Next
    INDEX
    Explanations

    protease, implementation, graphs, MOF, integer, variables, particulate, web, retina

    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
    usercontent
    -0.09
    _crypto
    -0.08
    éĥ½å¾Ī好
    -0.08
     semb
    -0.08
    ãģIJãĤĭ
    -0.08
    ÐijÐļ
    -0.08
    ropy
    -0.08
    elus
    -0.08
    .intent
    -0.08
    ecure
    -0.08
    POSITIVE LOGITS
    atch
    0.06
     ins
    0.06
    -themed
    0.06
     Ins
    0.06
    ritical
    0.06
    olis
    0.06
    -dominated
    0.06
    ä¸Ķåħ·æľī
    0.06
     Jack
    0.06
    -only
    0.06
    Activations Density 0.451%

    No Known Activations