© 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. 32180
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
    κά
    -0.07
     destruct
    -0.07
    PathComponent
    -0.07
    æµ·é»ĺ
    -0.07
    ç«¥åŃIJ
    -0.07
    \/
    -0.07
    åºĻä¼ļ
    -0.06
    lesen
    -0.06
    daw
    -0.06
    ctype
    -0.06
    POSITIVE LOGITS
    èĩ
    0.08
    adis
    0.07
    ŀ
    0.07
    Ĩµ
    0.07
     Meny
    0.07
    unga
    0.07
    itiba
    0.07
    rete
    0.06
    å£ĩ
    0.06
    鼶
    0.06
    Activations Density 0.002%

    No Known Activations