© 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. 30369
    Prev
    Next
    INDEX
    Explanations

    nuclear, orbital structure, separation

    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
    err
    -0.07
     discretionary
    -0.07
     duty
    -0.07
    kala
    -0.07
    转çĽĺ
    -0.06
    é»ĦçīĽ
    -0.06
     Dez
    -0.06
     toArray
    -0.06
    çĩĥæĶ¾
    -0.06
    åľ¨ç½ijç«Ļ
    -0.06
    POSITIVE LOGITS
    çĥ¯
    0.08
    ä¸įè¿ľ
    0.08
    è¶Ĭ强
    0.07
     Fran
    0.07
     вкладÑĭ
    0.07
     molecule
    0.07
    nodeName
    0.07
    Processor
    0.07
     McConnell
    0.07
     nuclei
    0.07
    Activations Density 0.009%

    No Known Activations