© 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. 58146
    Prev
    Next
    INDEX
    Explanations

    year end review

    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
    Ñģок
    -0.07
     Booth
    -0.06
    å¿ĥæĢ¥
    -0.06
     hierarchy
    -0.06
    ĩ
    -0.06
     Desp
    -0.06
     Penj
    -0.06
    ĥ
    -0.06
    atri
    -0.06
    .Encoding
    -0.06
    POSITIVE LOGITS
    è¿°èģĮ
    0.09
    åįĬå¹´çļĦ
    0.08
    è¿°
    0.08
    å±¥èģĮ
    0.08
    èĢķèĢĺ
    0.08
    oty
    0.08
     accomplishments
    0.08
    æ±ĩæĬ¥
    0.07
    äºĶå¹´çļĦ
    0.07
     satisf
    0.07
    Activations Density 0.010%

    No Known Activations