© 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. 23991
    Prev
    Next
    INDEX
    Explanations

    declaration or definition

    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
    对ä¸Ĭè¿°
    -0.07
    ill
    -0.07
    对该
    -0.07
    jar
    -0.07
    对ä»ĺ
    -0.06
    å°Ĩ该
    -0.06
    iller
    -0.06
    éĨī
    -0.06
    orman
    -0.06
    onical
    -0.06
    POSITIVE LOGITS
     variables
    0.10
    åıĺéĩı
    0.10
     ë³ĢìĪĺ
    0.09
     пеÑĢемен
    0.09
    variables
    0.09
     Variables
    0.09
    Variables
    0.09
    åıĺéĩıçļĦ
    0.09
    Vars
    0.07
     domic
    0.07
    Activations Density 0.005%

    No Known Activations