© 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. 17602
    Prev
    Next
    INDEX
    Explanations

    Here's the explanation for the neuron's behavior:**check out**

    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
     tempo
    -0.07
    vasti
    -0.06
    å¹ħ度
    -0.06
     Conti
    -0.06
    try
    -0.06
    度åĴĮ
    -0.06
    icarbon
    -0.05
    Ñģли
    -0.05
    צע
    -0.05
     impacts
    -0.05
    POSITIVE LOGITS
    ajah
    0.06
    enta
    0.05
    çľŁå¥½
    0.05
    ä¸ĢæĿ¡é¾Ļ
    0.05
    æĺİç¡®è§Ħå®ļ
    0.05
    urv
    0.05
    æ°ijåĪĿåŃĹ第
    0.05
    ç»Łæ²»
    0.05
    æĸĩæĺİ
    0.05
     destined
    0.05
    Activations Density 0.008%

    No Known Activations