© 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. 10866
    Prev
    Next
    INDEX
    Explanations

    domain names and urls

    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
    åħĥèµ·
    -0.09
    æĽ²å¼ł
    -0.08
    ormsg
    -0.08
    witz
    -0.08
    èĻ
    -0.08
    /DTD
    -0.08
    orm
    -0.08
    صÙĬب
    -0.08
    ofday
    -0.07
    DOMNode
    -0.07
    POSITIVE LOGITS
    çļĦäºĭæĥħ
    0.07
     sam
    0.07
    neh
    0.07
     specified
    0.07
     ÑıкобÑĭ
    0.07
    åģļçļĦäºĭæĥħ
    0.07
    æĢ§ä»¥åıĬ
    0.06
    etri
    0.06
    çļĦåĶ¯ä¸Ģ
    0.06
    .valid
    0.06
    Activations Density 0.001%

    No Known Activations