© 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. 8786
    Prev
    Next
    INDEX
    Explanations

    Exercise, Minister, Listed, Gifts, Anniversary

    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
    çij°
    -0.07
    ffel
    -0.07
    Ħ
    -0.07
     Presup
    -0.06
    为该
    -0.06
    enner
    -0.06
    æĺ¯è¯¥
    -0.06
    çŁ
    -0.06
    aldas
    -0.06
    ools
    -0.06
    POSITIVE LOGITS
    ãģĿãģ®ä»ĸ
    0.08
     lainnya
    0.08
     пÑĢоÑĩиÑħ
    0.08
    à¸Ńืà¹Īà¸Ļà¹Ĩ
    0.08
    })",
    0.07
    åħ¶å®ĥ
    0.07
    åħ¶ä»ĸçļĦ
    0.07
    horn
    0.07
    æ
    0.07
    ä¸ĢèĪ¬
    0.07
    Activations Density 0.046%

    No Known Activations