© 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. 65128
    Prev
    Next
    INDEX
    Explanations

    versus, vs, difference, or ratio

    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
    å°Ĩè¿Ļ个
    -0.07
    å°Ĩè¿Ļ
    -0.07
    å°Ĩå®ĥ
    -0.07
    对该
    -0.07
    ajak
    -0.07
    estan
    -0.07
    ixer
    -0.07
    åĪĻ该
    -0.07
    为该
    -0.07
    该车
    -0.07
    POSITIVE LOGITS
     versus
    0.10
     vs
    0.08
    è°ĵä¹ĭ
    0.07
    ãģłãģ£ãģŁãĤĬ
    0.07
    rient
    0.07
    issant
    0.06
    ãģļ
    0.06
    ield
    0.06
    ãģ£ãģŁãĤĬ
    0.06
    ÑģелÑĮ
    0.06
    Activations Density 0.922%

    No Known Activations