© 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. 11932
    Prev
    Next
    INDEX
    Explanations

    nucleation, initiation, seeding

    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
    ibbon
    -0.07
    кÑĥÑĢ
    -0.07
    _rat
    -0.07
    اضر
    -0.07
    ýt
    -0.07
    ãĤĴãĤģ
    -0.07
    çĶŁåij½ç§ijåѦ
    -0.06
    度çļĦ
    -0.06
    گرد
    -0.06
    .writeValue
    -0.06
    POSITIVE LOGITS
     seeding
    0.09
     espont
    0.09
     spontaneously
    0.08
     initiation
    0.08
     spontan
    0.08
    çļĦç§įåŃIJ
    0.08
    åIJ¯åĬ¨
    0.08
     initiating
    0.08
    .seed
    0.08
     seeds
    0.08
    Activations Density 0.015%

    No Known Activations