© 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. 13974
    Prev
    Next
    INDEX
    Explanations

    mutation and spontaneous changes

    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
    rah
    -0.08
     oddly
    -0.07
    chine
    -0.07
    orent
    -0.07
    yah
    -0.07
    ANH
    -0.06
    ODB
    -0.06
    inder
    -0.06
    åĽ½åĬ¡éĻ¢åĬŀåħ¬åİħ
    -0.06
    é¦
    -0.06
    POSITIVE LOGITS
     spontaneously
    0.10
     espont
    0.10
     spontaneous
    0.09
     spontan
    0.09
    åıijçĶŁçİĩ
    0.09
    èIJĮåıij
    0.08
    mutation
    0.08
    ç¨Ģæľī
    0.08
     randomly
    0.08
     spont
    0.08
    Activations Density 0.013%

    No Known Activations