© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17679
    Prev
    Next
    INDEX
    Explanations

    ages of children

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imb
    -0.06
    ining
    -0.06
    è¿ģ
    -0.05
     cho
    -0.05
    æķ°æĺ¯
    -0.05
    ty
    -0.05
    æķ°
    -0.05
    å¤ĸæĿ¥
    -0.05
    åIJİæĿ¥
    -0.05
    tele
    -0.05
    POSITIVE LOGITS
    دÙĪز
    0.06
    orer
    0.06
    é¾IJ
    0.06
    лÑİÑĤ
    0.06
    å·¨åħ½
    0.06
    itorium
    0.06
    ÑģÑĤÑģÑı
    0.06
    å·¨é¾Ļ
    0.06
    etur
    0.06
    ivia
    0.06
    Activations Density 0.016%

    No Known Activations