© 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. 3008
    Prev
    Next
    INDEX
    Explanations

    effects and consequences

    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
    holt
    -0.08
    iggio
    -0.08
    undy
    -0.08
    çŃīæĿIJæĸĻ
    -0.08
    亳
    -0.08
    åij¤
    -0.07
    autoload
    -0.07
    åºĶå½ĵä¾Ŀçħ§
    -0.07
    主åĬ¨åIJij
    -0.07
    并æĮī
    -0.07
    POSITIVE LOGITS
    åıĹåĪ°å½±åĵį
    0.08
    缴æİ¥çļĦ
    0.08
    缴æݥ影åĵį
    0.08
    éĹ´æİ¥
    0.08
    æľĢ缴æİ¥
    0.08
    çļĦåIJİæŀľ
    0.08
    åıĹå½±åĵį
    0.08
    åħįåıĹ
    0.08
     outcomes
    0.07
    ãģ«å½±éŁ¿
    0.07
    Activations Density 0.121%

    No Known Activations