© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 25609
    Prev
    Next
    INDEX
    Explanations

    interstellar gas, dust, and nebulae

    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
    ibat
    -0.07
    çī¡ä¸¹
    -0.07
    ünd
    -0.07
    æŃ¥æŃ¥
    -0.06
    åįķè¾¹
    -0.06
     Mud
    -0.06
    åľŁæĸ¹
    -0.06
     dese
    -0.06
    Ĭ
    -0.06
    平稳
    -0.06
    POSITIVE LOGITS
    ç¨Ģ
    0.10
    å¯Ĩäºij
    0.09
    nas
    0.08
    density
    0.08
    éĿ¢çº±
    0.08
     loãng
    0.08
     sparse
    0.08
    invisible
    0.08
    å¯Ĩ度
    0.08
    Sparse
    0.08
    Activations Density 0.025%

    No Known Activations