© 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. 11711
    Prev
    Next
    INDEX
    Explanations

    multitype, multigraph, multivalent, multilayer, multiset

    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
    lesia
    -0.08
    ptions
    -0.08
    اء
    -0.08
    earch
    -0.07
    NOWLED
    -0.07
    furt
    -0.07
    wards
    -0.07
    æĹłèĻij
    -0.07
    俱ä¹IJéĥ¨
    -0.07
    ãģ£ãģ±
    -0.07
    POSITIVE LOGITS
    pliers
    0.10
    кÑĢаÑĤно
    0.10
    å±Ĥ次çļĦ
    0.09
    lify
    0.09
    Ùijع
    0.08
    roit
    0.08
    /div
    0.08
    IPLE
    0.08
    enegro
    0.08
    ieur
    0.08
    Activations Density 0.036%

    No Known Activations