© 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. 51639
    Prev
    Next
    INDEX
    Explanations

    studied group, Monday, regards, dogs, format

    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
    kt
    -0.07
    åħ¶ä»ĸæĸ¹å¼ı
    -0.07
    _DER
    -0.06
    orie
    -0.06
     concl
    -0.06
    лÑĸн
    -0.06
    ä¸įå½ĵ
    -0.06
     cj
    -0.06
    å¸ĸ
    -0.06
    NS
    -0.06
    POSITIVE LOGITS
    ples
    0.07
    ä½İçĿĢ头
    0.07
    æŶèĩ³
    0.07
    azu
    0.07
    ÂŃt
    0.07
    SourceType
    0.07
    .datasource
    0.07
     tárgy
    0.07
    ãĤ·ãĥ¥ãĥ¼
    0.07
    ocide
    0.07
    Activations Density 0.543%

    No Known Activations