© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8636
    Prev
    Next
    INDEX
    Explanations

    testing frameworks and professional context

    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
    kel
    -0.08
    ÑĥÑĤÑĮ
    -0.08
    _secure
    -0.07
    erei
    -0.07
    åıĮåIJij
    -0.07
    utz
    -0.07
    å¿ħéľĢ
    -0.07
    pit
    -0.07
    å¿ħéľĢçļĦ
    -0.07
    bid
    -0.07
    POSITIVE LOGITS
    ä¸İä¹ĭ
    0.11
    çĽ¸å¯¹åºĶçļĦ
    0.10
    缸åºĶçļĦ
    0.09
    缸åĮ¹éħį
    0.09
    åºĶ以
    0.09
    缸åij¼åºĶ
    0.08
    对åºĶçļĦ
    0.08
    åĮ¹éħįçļĦ
    0.08
    缸åºĶ
    0.08
    缸æĩī
    0.08
    Activations Density 0.041%

    No Known Activations