© 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. 42404
    Prev
    Next
    INDEX
    Explanations

    for example, particular, especially

    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
     اÙĦØŃÙĬ
    -0.08
    ogna
    -0.07
    apak
    -0.07
    еÑĢна
    -0.07
    è¿ĺä¸İ
    -0.07
    iore
    -0.06
     backs
    -0.06
    ÛĮÙĤÛĮ
    -0.06
    abis
    -0.06
    eniable
    -0.06
    POSITIVE LOGITS
    æĺ¯åIJ¦åı¯ä»¥
    0.08
    æĺ¯åIJ¦åŃĺåľ¨
    0.07
    å¦Ĥæŀľåı¯ä»¥
    0.07
    ))?
    0.07
    请äºİ
    0.07
    rou
    0.07
     WHETHER
    0.07
     semb
    0.07
    æĺ¯åIJ¦èĥ½
    0.06
    æĺ¯åIJ¦éľĢè¦ģ
    0.06
    Activations Density 0.086%

    No Known Activations